A system and method for performing vision inspection on preinstalled photovoltaic modules

Abstract

The present invention relates to a system (101) and method (401) for performing vision inspection on at least one photovoltaic cell or module; said system (101) is capable to detect defects (102) in said photovoltaic cell or module (103) by detecting shadow representation on image captured by at least one detector (119) when said defect (102) obstructs transflected light in said photovoltaic cell or module (103); said light emitted from at least one first light source (115); wherein said system (101) further comprises of at least one second light source (118) to perform photoluminescence inspection on said photovoltaic cell or module (103).

Description

[0001] A SYSTEM AND METHOD FOR PERFORMING VISION INSPECTION ON

[0002] PREINSTALLED PHOTOVOLTAIC MODULES

[0003] 1. TECHNICAL FIELD OF THE INVENTION

[0004] The present invention relates to a system and method for performing vision inspection on at least one photovoltaic cell or module; said system is capable to detect defects in said photovoltaic cell or module by detecting shadow representation on image captured by at least one detector when said defect obstructs transflected light in said photovoltaic cell or module; said light emitted from at least one first light source; wherein said system further comprises of at least one second light source to perform photoluminescence inspection on said photovoltaic cell or module.

[0005] 2. BACKGROUND OF THE INVENTION

[0006] Currently, the kind of inspection methods used on preinstalled photovoltaic (PV) modules are visible light inspection, electroluminescence (EL), photoluminescence (PL) or thermal imaging. These inspection methods are commonly carried out by using a tripod mounted camera, handheld devices or with unmanned aerial vehicle such as drones. These inspection methods produce low resolution images, thus not able to detect fine defects on photovoltaic cells or modules. Furthermore, these inspection methods are time consuming because some of the inspection methods are done manually or some inspections need to be done with multiple rounds or repetitions on the same location in order to ascertain absence of defect on said photovoltaic cell or module.

[0007] There is another type of inspection where the photovoltaic cells or modules need to be powered up using reverse voltage so that manual inspection by the human can be done, thus increasing the risk of damaging the PV cells or modules.

[0008] Some of the inspection methods mentioned are very much affected by the ambient light, thus said inspection can typically be carried out when the ambient light is low, such as night time.

[0009] Hence, it would be advantageous to alleviate the shortcomings by having a system and method for performing vision inspection on at least one photovoltaic cell or module using at least one first light source to perform transflection (TF) inspection and at least one second light source to perform photoluminescence inspection on said photovoltaic cell or module.

[0010] 3. SUMMARY OF THE INVENTION

[0011] Accordingly, it is the primary aim of the present invention to provide a system for detecting defect in at least one preinstalled photovoltaic module (103) whereby the vision inspection module (109) comprises of both at least one first light source (115a) performing transflection (TF) inspection and at least one second light source (115b) performing photoluminescence inspection on said preinstalled photovoltaic module

[0012] (103). It is yet another objective of the present invention to provide a system for detecting defect in at least one preinstalled photovoltaic module (103) wherein usage of line scan camera as detector (119) produces high resolutions images.

[0013] It is yet another objective of the present invention to provide a system for detecting defect in at least one preinstalled photovoltaic module (103) whereby said inspection can be performed at any time of the day, including daytime.

[0014] It is yet another objective of the present invention to provide a system for detecting defect in at least one preinstalled photovoltaic module (103) whereby images produced by TF inspection are homogeneous and do not contain interfering or confusing noises compared to electroluminescence (EL) inspection method.

[0015] It is yet another objective of the present invention to provide a system for detecting defect in at least one preinstalled photovoltaic module (103) whereby TF inspection offers much higher resolution and accuracy in detecting microcracks compared to thermal inspection. It is yet another objective of the present invention to provide a system for detecting defect in at least one preinstalled photovoltaic module (103) whereby said inspection does not require electrical current to be introduced to said preinstalled PV module. Additional objects of the invention will become apparent with an understanding of the following detailed description of the invention or upon employment of the invention in actual practice.

[0016] According to the preferred embodiment of the present invention the following is provided:

[0017] A system for detecting defect in at least one preinstalled photovoltaic module comprising: at least one first axis (Y) and second axis (X) movement mechanism capable to be coupled on said preinstalled photovoltaic module; wherein said first axis (Y) and second axis (X) movement mechanism comprises of at least one frame with at least one pathway along a first axis (Y), said pathway capable of guiding movement of at least one vision inspection module along said first axis (Y); said pathway having a first end and a second end; wherein said first axis (Y) and second axis (X) movement mechanism further comprises of at least one frame actuating mechanism attached to any suitable position on said frame, capable of changing the position of said frame along a second axis (X), wherein said second axis (X) is substantially perpendicular to said first axis (Y); said vision inspection module further comprises of at least one light source positioned in a configuration capable to provide light to at least one region of said preinstalled photovoltaic module and at least one detector positioned in a configuration capable to detect at least one region on said preinstalled photovoltaic module where transflection of light occurs, at least one region on said preinstalled photovoltaic module where shadow representation is created by means of interruption to transmission of transflected light by said defect, or combination thereof; wherein said detector is further capable to detect at least one region on said preinstalled photovoltaic module where reflection of light occurs, at least one region on said preinstalled photovoltaic module where shadow representation is created by means of interruption to transmission of reflected light by said defect, or combination thereof; while said vision inspection module moves along said first axis (Y); said vision inspection module further comprises of at least one housing, covering the region on said preinstalled photovoltaic module to be inspected from direct sunlight, wherein said housing further covering said light source and said detector; said vision inspection module further comprises of at least one first actuator actuating said vision inspection module along said pathway; said first actuator of said vision inspection module and said frame actuating mechanism are powered by any suitable power source; at least one any suitable data processing system; characterized in that said light source comprises of at least one first light source positioned in a configuration whereby light path of said first light source when reaching first surface of said preinstalled photovoltaic module is substantially up to 20mm (A) from the field of view of said detector; said light passing said first surface is transflected within said preinstalled photovoltaic module resulting in illumination from subsurface of said preinstalled photovoltaic module; wherein said first light source emits light with wavelength of 1200nm to 1500nm; said light source further comprises of at least one second light source positioned in a configuration whereby light path of said second light source when reaching said first surface of said preinstalled photovoltaic module is substantially aligned to the field of view of said detector; said second light source emits light with any suitable wavelength shorter than near infrared (NIR).

[0018] In another embodiment of the invention there is provided:

[0019] A method for detecting defect in at least one preinstalled photovoltaic module comprising the steps of: (i) capturing at least one image of a region on said preinstalled photovoltaic module by at least one detector; wherein said preinstalled photovoltaic module is illuminated by at least one first light source or at least one second light source wherein said first light source provides light that reaches a first surface of said preinstalled photovoltaic module at substantially up to 20mm (A) from the field of view of said detector; said light passing said first surface is transflected within said preinstalled photovoltaic module resulting in illumination from a subsurface of said preinstalled photovoltaic module wherein said first light source emits light with wavelength of 1200nm to 1500nm; wherein said second light source provides light that reaches said first surface of said preinstalled photovoltaic module at substantially aligned to the field of view of said detector wherein said second light source emits light with any suitable wavelength shorter than near infra-red (NIR);

[0020] (ii) segmenting said image using any suitable rule-based algorithm;

[0021] (iii) analysing said segmented image to determine whether any defects are detected;

[0022] (iv) extracting and classifying feature of defect, if defect is detected, based on shape and size; (v) identifying said preinstalled photovoltaic module as having defect if shape and size of said defect comprises of at least one dark cell more than a specified area of preinstalled photovoltaic module, at least one finger mark, at least one spider crack, at least one line crack, at least one chipping at least one dark spot or combination thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other aspect of the present invention and their advantages will be discerned after studying the Detailed Description in conjunction with the accompanying drawings in which:

[0024] FIG 1A is a side view while FIG IB is the top view of the system of the present invention being mounted on at least one preinstalled photovoltaic module while FIG 1C is the exploded view of the first axis (Y) and second axis (X) movement mechanism.

[0025] FIG 2 further shows the transflected light in said photovoltaic cell or module.

[0026] FIG 3 shows a sample of an image captured by the detector.

[0027] FIG 4 shows a flowchart of the method for detecting defect in at least one preinstalled photovoltaic module of the present invention.

[0028] FIG 5A, FIG 5B and FIG 5C show the flow of identifying spider crack.

[0029] FIG 6A, 6C, 6E, 6G and 61 show samples of raw images captured by said detector while FIG 6B, 6D, 6F, 6H and 6J show the corresponding images of images from FIG 6A, 6C, 6E, 6G and 61 respectively after being performed step (ii) of the method of the present invention, wherein said step (ii) is segmenting said image taken by said detector.

[0030] 5. DETAILED DESCRIPTION OF THE DRAWINGS

[0031] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by the person having ordinary skill in the art that the invention may be practised without these specific details. In other instances, well known methods, procedures and / or components have not been described in detail so as not to obscure the invention.

[0032] The invention will be more clearly understood from the following description of the embodiments thereof, given by way of example only with reference to the accompanying drawings, which are not drawn to scale.

[0033] As shown in FIG 1A, the present invention presents a system (101) for performing vision inspection to detect defect (102) in at least one preinstalled photovoltaic module (103) comprising of at least one vision inspection module (109) and at least one any suitable data processing system (106); wherein said vision inspection module (109) comprises of at least one detector (119), at least one first light source (115a) and at least one second light source (115b). The system (101) is arranged such that the inspection is done while said vision inspection module (109) and said preinstalled photovoltaic module (103) moves in relation to each other. In other words, during inspection, the first scenario is that the vision inspection module (109) moves while the preinstalled photovoltaic (103) is stationary. This is because the typical type of detector (119) used is line scan camera, which requires capturing of image to be done while the object or detector is moving. However, it is also possible for area scan camera to be used as the detector (119).

[0034] The detector (119) is positioned in a configuration capable to detect at least one region on said preinstalled photovoltaic module (103). As shown in FIG 2, The first light source (115a) is meant to perform transflection (TF) inspection; is positioned in a configuration whereby light path of said first light source (115a) when reaching a first surface (116) of said preinstalled photovoltaic (103) is substantially 10-20mm (A) from the field of view of said detector (119). One example of the position of the first light source (115a) is whereby the light path of said first light source (115a) when reaching said first surface (116) of said preinstalled photovoltaic module (103), to be substantially perpendicular to said first surface (116). However, it is also possible, due to physical constraints of the detector (119) and the first light source (115a), to have the detector (119) and the first light source (115a) to be substantially close to each other, which will require the first light source (115a) to be tilted towards the detector's field of view.

[0035] The first surface (116) is typically the surface of the preinstalled photovoltaic module (103) facing the detector (119), first light source (115a) and second light source (115b). After the light from said first light source (115a) passes said first surface (116), said light is transflected within said preinstalled photovoltaic module (103) resulting in illumination from subsurface (117) of said preinstalled photovoltaic module (103). The subsurface (117) is generally the inner surface of said preinstalled photovoltaic module (103) facing said light path after said light path passes said first surface (116).

[0036] As shown in FIG 2, when the tranflected light (123) meets with defect (102) inside said preinstalled photovoltaic module (103), said transflected light (123) will be interrupted or reflected back, creating a shadow representation (121) that can be detected by said detector (119). The shadow representation (121) is generally created because the transflected light (123) is not able to pass the defect (102), causing the opposite side of the defect (102) to be darker compared to other regions when image is taken by said detector (119). FIG 3 shows a sample of an image (301) captured by the detector (119) showing the defect (102) and shadow representation (121).

[0037] The first light source (115a) is capable of emitting light with wavelength of 1200nm to 1500nm. It is important for the first light source (115a) to be positioned in such and emitting said light wavelength to create the transflection effect in said preinstalled photovoltaic module (103). The first light source (115a) can be near infrared (NIR) laser line light, short wave infrared (SWIR) laser line light, or any other suitable line light capable of producing transflected light within said preinstalled photovoltaic module (103).

[0038] The second light source (115b) is meant to perform photoluminescence (PL) inspection; is positioned in a configuration whereby light path of said second light source (115b) when reaching said first surface (116) of said preinstalled photovoltaic module (103) is substantially aligned to the field of view of said detector (119); said second light source (115b) emits light with any suitable wavelength shorter than near infrared (NIR). The second light source (115b) can be visible light emitting diode (LED) line light or near infrared LED line light. The first light source (115a) and second light source (115b) are both not being turned on at any same time to enable transflection (TF) and photoluminescence (PL) inspection to be done separately.

[0039] The detector (119) is positioned to be able to detect at least one region on said preinstalled photovoltaic module (103). The region may show transflection of light when there is no defect (102) and may show said shadow representation (121) in the presence of defect (102). If line scan camera is used as the detector (119), said line scan camera will scan the first surface (116) of said preinstalled photovoltaic module (103) as the detector (119) and preinstalled photovoltaic module (103) move in relation to each other. The detector (119) can be near infrared (NIR) line scan camera, short wave infrared (SWIR) line scan camera or any other suitable detector (119).

[0040] The system (101) of the present invention can be utilized to inspect said preinstalled photovoltaic module (103) in various scenarios or applications. One of the possible scenarios is where said inspection is done after a single photovoltaic module (103) or an array of multiple photovoltaic modules are being preinstalled on any suitable structure such as buildings, vehicles, or any other location suitable for a solar farm, as shown in FIG 1A and FIG IB, whereby the system (101) moves while the photovoltaic module (103) is stationary. In various scenarios, the same vision inspection module (109) can be used even though extra setup is added to perform the inspection in the various scenarios.

[0041] As shown in FIG 1A, FIG IB and FIG 1 C, which show an example of the system being used in the first scenario, whereby the system (101) further comprises of at least one first axis (Y) and second axis (X) movement mechanism capable to be coupled on said preinstalled photovoltaic module (103).

[0042] As shown in FIG 1C, the first axis (Y) and second axis (X) movement mechanism (104) comprises of at least one frame with at least one pathway (107a, 107b) along a first axis (Y), said pathway (107a, 107b) capable of guiding movement of at least one vision inspection module (109) along said first axis (Y). The pathway (107a, 107b) can be rails, tracks or any other suitable pathway capable of guiding movement of said vision inspection module (109). The pathway (107a, 107b) has a first end (110a) and a second end (110b). The first axis (Y) and second axis (X) movement mechanism (104) further comprises of at least one frame actuating mechanism (113) attached to any suitable position on said frame, capable of changing the position of said frame along a second axis (X), wherein said second axis (X) is substantially perpendicular to said first axis (Y). For example, the frame actuating mechanism (113) can be attached to said first end (110a) and said second end (110b) of said pathway (107a, 107b).

[0043] The vision inspection module (109) further comprises of at least one first actuator (127) actuating said vision inspection module (109) along said pathway (107a, 107b). The first actuator (127) of said vision inspection module (109) and said frame actuating mechanism (113) are powered by any suitable power source (129), such as solar powered battery, battery, direct power through cable, or any other suitable power source.

[0044] The vision inspection module (109) further comprises of at least one housing (125), covering the region on said preinstalled photovoltaic module (103) to be inspected from direct sunlight, wherein said housing (125) further covering said first light source (115a), said second light source (115b) said detector (119). The purpose of the housing (125) is to provide a certain level of shading on the region that is being inspected on the preinstalled photovoltaic module (103), especially on the detector's (119) field of view, apart from also covering the other electrical components. It is understood that the configuration of the first axis (Y) and second axis (X) movement mechanism is just one example of the many possible ways to control position of the vision inspection module (109) to perform vision inspection on preinstalled photovoltaic module (103).

[0045] The frame actuating mechanism (113) further comprises of at least one guiding element (301) in position capable of aligning said frame actuating mechanism (113) with said preinstalled photovoltaic module (103) to enable movement of said frame actuating mechanism (113) with reference to said preinstalled photovoltaic module (103) in said second axis (X). The guiding element (301) can be rollers, proximity sensors, or any other suitable guiding element along a surface. In the first scenario, the system (101) further comprises of at least one remote control device 131 capable to be used by at least one user to control operation of said system (101).

[0046] In other words, the inspection is done on the first axis (Y), while the second axis (X) movement is to shift the system (101) to the next column of the preinstalled photovoltaic module (103) to be inspected, and also to enable inspection of multiple preinstalled photovoltaic modules (103) placed in a row.

[0047] The present invention is also a method (401) for detecting defect (102) in at least one preinstalled photovoltaic module (103) the following steps, as shown in FIG 4. In step (i) (403), at least one image (301) of a region on said preinstalled photovoltaic module (103) is captured by at least one detector (119). The preinstalled photovoltaic module (103) is illuminated by at least one first light source (115a) or at least one second light source (115b). The first light source (115a) provides light that reaches a first surface (116) of said preinstalled photovoltaic module (103) at substantially up to 20mm (A) from the field of view of said detector (119); said light passing said first surface (116) is transflected within said preinstalled photovoltaic module (103) resulting in illumination from a subsurface (117) of said preinstalled photovoltaic module (103). The first light source (115a) emits light with wavelength of 1200nm to 1500nm. The second light source (115b) provides light that reaches said first surface (116) of said preinstalled photovoltaic module (103) at substantially aligned to the field of view of said detector (119). The second light source (115b) emits light with any suitable wavelength shorter than near infra-red (NIR). In step (ii) (405), said image (301) is segmented using any suitable rule-based algorithm. Rule-based algorithm comprises of image preprocessing techniques such as filtering or noise reduction which is applied to said image (301) to improve the visibility of the defects (102) in said image (301), before utilizing any suitable thresholding method to segment said image (301) into foreground region(s) (which may comprise of defect(s)) and background region(s). FIG 6A, 6C, 6E, 6G and 61 show samples of raw images captured by said detector while FIG 6B, 6D, 6F, 6H and 6J show the corresponding images of images from FIG 6A, 6C, 6E, 6G and 51 respectively after being performed step (ii) of the method of the present invention. In step (iii) (407), said segmented image is analysed to determine whether any defects are detected.

[0048] In step (iv) (409), if defect (102) is detected, feature of defect (102) is extracted and classified based on shape and size. Step (iv) comprises of the following sub-steps. In sub-step (iv)(a), algorithmic application of graph theory such as connected component analysis is performed on the binary image (301) to identify individual defect regions. In sub-step (iv)(b), filtering criteria is applied to said image to eliminate small or irrelevant components based on size and shape, wherein threshold values are set for minimum and maximum allowable sizes to filter out noise or very large objects. In sub-step (iv)(c), morphological operations like erosion and / or dilation are used to refine the shape of said defects (102).

[0049] In step (v) (411), said preinstalled photovoltaic module (103) is identified as having defect (102) if shape and size of said defect (102) comprises of at least one dark cell more than a specified area of preinstalled photovoltaic module (103), at least one finger mark, at least one spider crack (501), at least one line crack, at least one chipping, at least one dark spot or combination thereof. Preferably, said dark cell should not be more than 20% of the area of the preinstalled photovoltaic module (103), but other suitable thresholds may also be used.

[0050] The spider crack (501), as shown in FIG 5A, is identified in step (v) using the following sub-steps. In step (v)(a), all end point points (503) of said spider crack (501) are applied with convex hull algorithm to create an enclosed convex hull area (505) from the surrounding background, as shown in FIG 5B. In step (v)(b), a plurality of regions (507) is created from said enclosed convex hull area (505) separated by lines of said spider crack (501), as shown in FIG 5C. This is done by computing shape descriptors for each remaining defect region, including area, compactness, circularity, and other relevant measures. Thereafter, the area and centre of the input regions I defect regions are determined. The area represents the total number of pixels within the region, while the centre is determined by calculating the mean values of the line and column coordinates for all the pixels. Additionally, the convexity of each input region is calculated. A texture analysis method is incorporated to extract textural characteristics that capture the relative positions of neighbouring pixels. Thereafter, the most discriminative features that can effectively distinguish between different crack types and noises are identified. In step (v)(c), said regions (507) are counted using Euler number whereby said defect (102) is defined as spider crack (501) if there are more than three regions (507) in the same defect. Euler number can be calculated by the difference between the number of connected components and the number of holes in the regions. The spider cracks (501) can be normal spider crack, small spider crack or small spider crack on busbars. The line cracks can be normal line crack, baby line crack or short line crack at edges.

[0051] While the present invention has been shown and described herein in what are considered to be the preferred embodiments thereof, illustrating the results and advantages over the prior art obtained through the present invention, the invention is not limited to those specific embodiments. Thus, the forms of the invention shown and described herein are to be taken as illustrative only and other embodiments may be selected without departing from the scope of the present invention, as set forth in the claims appended hereto.

Claims

WHAT IS CLAIMED IS:

1. A system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) comprising: at least one first axis (Y) and second axis (X) movement mechanism (104) capable to be coupled on said preinstalled photovoltaic module (103); wherein said first axis (Y) and second axis (X) movement mechanism (104) comprises of at least one frame (105) with at least one pathway (107a, 107b) along a first axis (Y), said pathway (107a, 107b) capable of guiding movement of at least one vision inspection module (109) along said first axis (Y); said pathway (107a, 107b) having a first end (110a) and a second end (110b); wherein said first axis (Y) and second axis (X) movement mechanism (104) further comprises of at least one frame actuating mechanism (113) attached to any suitable position on said frame (105), capable of changing the position of said frame (105) along a second axis (X), wherein said second axis (X) is substantially perpendicular to said first axis (Y); said vision inspection module (109) further comprises of at least one light source (115a, 115b) positioned in a configuration capable to provide light to at least one region of said preinstalled photovoltaic module (103) and at least one detector (119) positioned in a configuration capable todetect at least one region on said preinstalled photovoltaic module (103) where transflection of light occurs, at least one region on said preinstalled photovoltaic module (103) where shadow representation (121) is created by means of interruption to transmission of transflected light (123) by said defect (102), or combination thereof; wherein said detector (119) is further capable to detect at least one region on said preinstalled photovoltaic module (103) where reflection of light occurs, at least one region on said preinstalled photovoltaic module (103) where shadow representation (121) is created by means of interruption to transmission of reflected light (123) by said defect (102), or combination thereof; while said vision inspection module (109) moves along said first axis (Y); said vision inspection module (109) further comprises of at least one housing (125), covering the region on said preinstalled photovoltaic module (103) to be inspected from direct sunlight, wherein said housing (125) further covering said light source (115a, 115b) and said detector (119); said vision inspection module (109) further comprises of at least one first actuator (127) actuating said vision inspection module (109) along said pathway (107a, 107b);said first actuator (127) of said vision inspection module (109) and said frame actuating mechanism (113) are powered by any suitable power source (129); at least one any suitable data processing system (106); characterized in that said light source (115a, 115b) comprises of at least one first light source (115a) positioned in a configuration whereby light path of said first light source (115a) when reaching first surface (116) of said preinstalled photovoltaic module (103) is substantially up to 20mm (A) from the field of view of said detector (119); said light passing said first surface (116) is transflected within said preinstalled photovoltaic module (103) resulting in illumination from subsurface (117) of said preinstalled photovoltaic module (103); wherein said first light source (115a) emits light with wavelength of 1200nm to 1500nm; said light source further comprises of at least one second light source (115b) positioned in a configuration whereby light path of said second light source (115b) when reaching said first surface (116) of said preinstalled photovoltaic module (103) is substantially aligned to the field of view of said detector (119); said second light source (115b) emits light with any suitable wavelength shorter than near infrared (NIR).

2. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said preinstalled photovoltaic module (103) is being inspected after said photovoltaic module (103) being preinstalled on a surface.

3. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said first light source (115a) and second light source (115b) are both not being turned on at any same time to enable transflection (TF) and photoluminescence (PL) inspection to be done separately.

4. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said pathway (107a, 107b) is rail, track or any other suitable pathway capable of guiding movement of said vision inspection module (109).

5. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said power source (129) is solar powered battery, battery, direct power through cable, or any other suitable power source.

6. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said frame actuating mechanism (113) is attached to said first end (110a) and said second end (110b) of said pathway (107a, 107b).

7. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1 or 6, wherein said frame actuating mechanism (113) further comprises of at least one guiding element (301) in position capable of aligning said frame actuating mechanism (113) with said preinstalled photovoltaic module (103) to enable movement of said frame actuating mechanism (113) with reference to said preinstalled photovoltaic module (103) in said second axis (X).

8. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 7 , wherein said guiding element (301) is roller, proximity sensor, or any other suitable guiding element along a surface.

9. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said detector (119) is near infrared (NIR) line scan cmera, short wave infrared (SWIR) line scan camera or any other suitable detector (119).

10. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said first light source (115a) is near infrared (NIR) laser line light, short wave infrared (SWIR) laser line light, or any other suitable line light capable of producing transflected light within said preinstalled photovoltaic module (103).

11. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said system (101) further comprises of at least one remote control device (131) capable to be used by at least one user to control operation of said system (101).

12. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1, wherein said second light source (115b) is positioned such that light emitted from said second light source (115b) reaches said preinstalled photovoltaic module (103) at an angle between 30° and 90°, provided said second light source (115b) does not occlude said detector (109).

13. The system (101) for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 1 , wherein said first light source (115a) and second light source (115b) are positioned as close as possible to said preinstalled photovoltaic module (103)., as long as said first light source (115a) and second light source (115b) do not occlude said detector (119) and not touching said preinstalled photovoltaic module (103).

14. A method (401) for detecting defect (102) in at least one preinstalled photovoltaic module (103) comprising the steps of:(i) capturing (403) at least one image (301) of a region on said preinstalled photovoltaic module (103) by at least one detector (119); wherein said preinstalled photovoltaic module (103) is illuminated by at least one first light source (115a) or at least one second light source (115b) wherein said first light source (115a) provides light that reaches a first surface (116) of said preinstalled photovoltaic module (103) at substantially up to 20mm (A) from the field of view of said detector (119); said light passing said first surface (116) is transflected within said preinstalled photovoltaic module (103) resulting in illumination from a subsurface (117) of said preinstalled photovoltaic module (103) wherein said first light source (115a) emits light with wavelength of 1200nm to 1500nm; wherein said second light source (115b) provides light that reaches said first surface (116) of said preinstalled photovoltaic module (103) at substantially aligned to the field of view of said detector (119) wherein said second light source (115b) emits light with any suitable wavelength shorter than near infra-red (NIR);(ii) segmenting (405) said image (301) using any suitable rule-based algorithm;(iii) analysing (407) said segmented image to determine whether any defects are detected;(iv) extracting and classifying (409) feature of defect (102), if defect (102) is detected, based on shape and size;(v) identifying (411) said preinstalled photovoltaic module (103) as having defect (102) if shape and size of said defect (102) comprises of at least one dark cell more than a specified area of preinstalled photovoltaic module (103), at least one finger mark, at least one spider crack (501), at least one line crack, at least one chipping, at least one dark spot or combination thereof.

15. The method for detecting defect (102) in at least one preinstalled photovoltaic module (103) as claimed in Claim 14, wherein said spider crack (501) is identified in step (v) using the following sub-steps:(a) applying convex hull algorithm to all end point (503) of said spider crack (501) to create an enclosed convex hull area (505) from the surrounding background;(b) creating a plurality of regions (507) from said enclosed convex hull area (505) separated by lines of said spider crack (501);(c) counting said regions (507) using Euler number whereby said defect (102) is defined as spider crack (501) if there are more than three regions (507) in the same defect.

Images