Offshore wind turbine generator blade fault mode characterization method, system and equipment and storage medium thereof

Abstract

The invention discloses an offshore wind turbine generator blade fault mode characterization method, system and device and a storage medium thereof, and belongs to the field of wind turbine generator state monitoring, and the method comprises the steps: obtaining noise feature information according to blade noise information; meanwhile, performing feature extraction on the leaf image information to obtain image feature information; meanwhile, blade load information is analyzed to obtain blade bending moment information, and blade acceleration information is analyzed to obtain blade vibration information; blade structure fault information is obtained through the noise feature information and the image feature information; meanwhile, according to the multiple pieces of blade bending moment information, blade consistency information is obtained through comparison, and then blade operation fault information is obtained in combination with blade vibration information; and according to the blade structure fault information and the blade operation fault information, analyzing and representing a blade fault mode. According to the method, the problem that the real-time state monitoring cannot be performed on the fan blade in the prior art can be solved, the offshore wind turbine generator can be monitored in real time, and meanwhile, the corresponding fault mode of the blade is represented.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of wind turbine condition monitoring, in particular to a wind turbine blade fault mode characterization method, system, device and storage medium thereof. BACKGROUND

[0002] The offshore wind turbine is a wind turbine applied to offshore wind power. As an important part of renewable energy, it has broad development prospects and great market potential. However, its design and operation face more complex and severe challenges than onshore wind turbines. The marine environment where the offshore wind turbine is located is extremely complex and changeable, and it faces many challenges from adverse factors, such as high atmospheric humidity and salt spray concentration, long hours of sunshine, frequent dry-wet alternating phenomena in splash areas, and long-term seawater immersion and serious attachment of aquatic organisms in underwater areas. These environmental factors undoubtedly bring great pressure and risk to the long-term, safe and stable operation of offshore wind power equipment.

[0003] The blade is the main component of the offshore wind turbine. Once a fault occurs during operation, it will cause the generator set to reduce efficiency or even stop, resulting in significant economic losses. At the same time, due to the remote location of the wind power plant, it is inconvenient to maintain and repair the equipment. The average time to remove the blade fault can be up to 10 days, which severely restricts the output of the wind turbine. And with the increase of installation depth and off-shore distance, it will inevitably lead to longer repair time. Therefore, real-time condition monitoring of the wind turbine blade, timely detection of faults and maintenance are of great significance to safety production. SUMMARY

[0004] The purpose of the present application is to provide an offshore wind turbine blade fault mode characterization method, system, device and storage medium to solve the problem that the prior art cannot perform real-time condition monitoring of the wind turbine blade, and to enable real-time monitoring of the offshore wind turbine while characterizing the corresponding fault mode of the blade.

[0005] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0006] A method for characterizing a fault mode of a blade of an offshore wind turbine generator set, comprising the following steps: collecting blade noise information, blade image information, blade load information and blade acceleration information; extracting noise characteristic values according to the blade noise information to obtain noise characteristic information; simultaneously extracting features from the blade image information to obtain image feature information; simultaneously analyzing the blade load information to obtain blade bending moment information and analyzing the blade acceleration information to obtain blade vibration information; identifying blade structural fault information corresponding to different characteristic information through the noise characteristic information and the image feature information; simultaneously comparing blade consistency information obtained from a plurality of blade bending moment information, and then combining the blade vibration information to obtain blade operation fault information; and analyzing and characterizing the blade fault mode according to the blade structural fault information and the blade operation fault information.

[0007] In some embodiments, the blade noise information includes aerodynamic noise, mechanical noise and electromagnetic noise.

[0008] In some embodiments, after collecting the blade noise information, the blade noise information is filtered and denoised to remove the mechanical noise and the electromagnetic noise.

[0009] In some embodiments, the noise characteristic information includes rotating noise characteristic information, turbulent inflow noise characteristic information and airfoil self-excitation noise characteristic information.

[0010] In some embodiments, the step of identifying blade structural fault information corresponding to different characteristic information through the noise characteristic information and the image feature information specifically includes: preliminarily analyzing blade frequency information through the rotating noise characteristic information, and then further analyzing blade shape information and blade roughness information by combining the turbulent inflow noise characteristic information and the airfoil self-excitation noise characteristic information; and simultaneously using a convolutional neural network to detect and identify blade surface defect information according to the image feature information; the blade structural fault information includes blade frequency information, blade shape information, blade roughness information and blade surface defect information.

[0011] In some embodiments, the step of comparing blade consistency information obtained from a plurality of blade bending moment information, and then combining the blade vibration information to obtain blade operation fault information specifically includes: comparing blade consistency information through blade bending moment information of three blades of the same wind turbine generator at the same cross section; taking blade vibration information when the blade is normally running as a standard, obtaining first blade operation fault information, second blade operation fault information and third blade operation fault information according to the blade consistency information and the blade vibration information; and the blade operation fault information includes the first blade operation fault information, the second blade operation fault information and the third blade operation fault information.

[0012] In some embodiments, the step of analyzing and characterizing the blade failure mode according to the blade structure failure information and the blade operation failure information specifically comprises: the blade structure failure information comprises blade frequency information, blade shape information, blade roughness information and blade surface defect information; according to the blade frequency information and the corresponding blade operation failure information, the corresponding blade failure mode is characterized as a sand hole and a cavity; according to the blade shape information, the blade roughness information and the corresponding blade operation failure information, the corresponding blade failure mode is characterized as blade icing; and according to the blade surface defect information and the corresponding blade operation failure information, the corresponding blade failure mode is characterized as a surface crack and a surface opening.

[0013] A blade failure mode characterization system for offshore wind turbine units comprises:

[0014] An information acquisition module is configured to acquire blade noise information, blade image information, blade load information and blade acceleration information.

[0015] A feature information extraction module is configured to extract noise feature values according to the blade noise information to obtain noise feature information, and to obtain image feature information by pre-processing and feature extraction on the blade image information, and to obtain blade bending moment information by analyzing the blade load information and blade vibration information by analyzing the blade acceleration information.

[0016] A failure information analysis module is configured to identify blade structure failure information corresponding to different feature information through the noise feature information and the image feature information, and to obtain blade consistency information by comparison according to a plurality of blade bending moment information, and to obtain blade operation failure information in combination with the blade vibration information.

[0017] A failure mode characterization module is configured to analyze and characterize the blade failure mode according to the blade structure failure information and the blade operation failure information.

[0018] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable in the processor, and the processor implements the steps of the offshore wind turbine unit blade failure mode characterization method when executing the computer program.

[0019] A computer readable storage medium stores a computer program, and the computer program implements the steps of the offshore wind turbine unit blade failure mode characterization method when executed by a processor.

[0020] Compared with the prior art, the present application has the following beneficial effects:

[0021] The application provides a offshore wind turbine blade fault mode characterization method, extracts noise feature information, image feature information, blade bending moment information and blade vibration information in blade noise information, blade image information, blade load information and blade acceleration information, obtains blade structure fault information and blade operation fault information, and finally characterizes different fault modes of the blade. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 A offshore wind turbine blade fault mode characterization system structure schematic diagram provided by the embodiment of the application is provided.

[0023] Figure 2 A offshore wind turbine blade fault mode characterization method flow schematic diagram provided by the embodiment of the application is provided.

[0024] Figure 3 An electronic equipment structure schematic diagram used by the embodiment of the application is provided. DETAILED DESCRIPTION

[0025] In order for those skilled in the art to better understand the application scheme, the technical scheme of the application will be further described in detail below in combination with the drawings, and the content is an explanation of the application rather than a limitation.

[0026] It should be noted that the terms "include" and "have" and any variations thereof in the specification and claims of the application are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device containing a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, systems, products or devices.

[0027] Firstly, the main indicators of the blade representing its fault state are introduced, mainly through the crack detection and icing detection to represent the blade fault mode, wherein the crack detection is analyzed by monitoring the related parameters of the blade vibration, combined with the peak value ratio algorithm, to predict the fault mode of the blade; the icing detection is fitted by monitoring the related parameters of the blade and the environmental parameters, and then the icing of the blade is predicted through difference analysis.

[0028] The blade fault mode mainly includes surface cracks and surface cracking, sand holes and cavities, and blade icing; the generation of surface cracks / cracking: during the installation process, the large volume of the blade brings certain risks to the installation construction, which may cause small human damage and lay hidden dangers for the future larger damage of the blade. In addition, long-term exposure and mechanical vibration can also cause crack damage of the wind turbine blade. Once the crack is formed, these cracks are continuously eroded by sand in the air, further causing more serious consequences, and even leading to blade rupture and collapse of the entire structure.

[0029] The generation principle of sand holes / cavities: for the wind turbine set working in outdoor environment all year round, it is often exposed to some harsh environments such as wind sand, rain and snow, salt spray, high temperature exposure, low temperature freezing, etc. Long-term erosion of rain and snow causes the protective glue on the surface of the blade to fall off, the plasticity to decrease, the brittleness to increase, combined with the beating of wind sand, the blade surface is easy to appear small and dense sand holes, and continue to worsen to form larger cavities, causing environmental foreign matter to invade the inside of the blade. Such damage is most common in the blade tip and blade edge of the windward surface, as shown in the following figure. When the blade appears similar damage, according to the on-site survey, during the operation process, it will emit a continuous howling sound. Therefore, through the on-site survey of the damaged blade and the ear listening experience of experienced workers, there is a relatively obvious difference in the aural perception of the aerodynamic audio signals generated by the damaged blade and the normal blade, mainly in the difference of tone and loudness.

[0030] The generation principle of blade icing: in the winter in many southern regions, due to the influence of climate, the surface of the wind turbine blade is easy to freeze. The icing has a great influence on the output and safe operation of the unit. The icing of the blade will change the shape and roughness of the blade airfoil, affect the original aerodynamic performance of the blade, and cause the failure of the blade itself and even other components of the unit.

[0031] Therefore, in order to monitor the running state of the blade in real time and represent the blade fault mode, the embodiment provides a wind turbine blade fault mode representation method, which specifically comprises the following steps:

[0032] Step 1: Acoustic sensors, wind speed sensors, and wind direction sensors are used to collect blade noise information of the wind turbine, and filtering and noise reduction are performed to remove irrelevant noise information such as mechanical noise and electromagnetic noise generated during blade rotation; at the same time, drones are used to collect blade image information, and load sensors and MEMS fiber optic accelerometers at the measuring points of the wind turbine blades are used to collect blade load information and blade acceleration information respectively.

[0033] Wind turbine noise can be mainly divided into two categories: aerodynamic noise during blade rotation and mechanical noise during gearbox rotation. Mechanical noise accounts for a relatively small proportion of wind turbine noise. As wind turbines become larger, the tip speed ratio is increased to improve wind energy utilization, which gradually increases the aerodynamic noise caused by blade rotation. Therefore, the measurement of wind turbine noise mainly focuses on aerodynamic noise.

[0034] Aerodynamic noise is mainly classified into three categories: rotational noise, turbulent inflow noise, and airfoil self-excitation noise. Rotational noise is generated by the periodic rotation of the blades, which interact with the air, causing pressure pulsations. These pressure pulsations can be considered as a steady-state constant and the sum of a series of pulsations according to Fourier series. Turbulent inflow noise is the noise radiated by Reynolds stress in the flow, mainly generated by the interaction between the blades and the turbulent airflow blowing towards them. When the Reynolds number is small, the fluid flows in stratified layers, with no interference between layers. As the Reynolds number increases, the streamlines become unstable, and adjacent layers influence each other. When the Reynolds number increases to a certain value, the streamlines become complex, forming many vortices of varying sizes, resulting in the transfer of mass and momentum—a phenomenon known as turbulence. Turbulent vortices vary in size, and large vortices continuously break down into smaller ones during flow. These smaller vortices gradually dissipate under the influence of viscous forces. Therefore, during the rotation of the fan, the blades interact with these vortices, thus generating turbulent inflow noise. The magnitude of turbulent noise is related to the size of the turbulent vortices and the blade chord length. Low-frequency noise is generated when the turbulent vortices are much larger than the chord length, while high-frequency noise is generated when they are much smaller. Airfoil self-excited noise is caused by the aerodynamics itself and cannot be avoided; it can only be reduced through certain methods. This noise mainly consists of trailing edge noise from the turbulent boundary layer and separation flow noise. When the Reynolds number reaches a certain value, the laminar flow on the blade surface will transform into turbulent flow, and the corresponding turbulent boundary layer will flow. When it reaches the trailing edge, the turbulence generates pressure fluctuations between the suction and pressure surfaces, thus producing trailing edge noise from the turbulent boundary layer. Because the Reynolds number is generally high when the wind turbine is operating, this noise accounts for a large proportion of the overall noise. When the angle between the incoming flow direction and the chord line is large, the turbulence at the leading edge of the suction surface intensifies, and the turbulent boundary layer will separate at the suction surface, thus forming separation flow noise, which accounts for a large proportion of the aerodynamic noise.

[0035] Step 2: By analyzing the blade noise information, feature values ​​are extracted to obtain rotational noise feature information, turbulent inflow noise feature information, and airfoil self-excitation noise feature information; and image feature information is obtained by extracting blade image information through a convolutional neural network; at the same time, blade load information and blade acceleration information are analyzed to obtain blade bending moment information and blade vibration information, respectively.

[0036] Specifically, the blade bending moment information is obtained by monitoring the bending moment at each section of the blade using load sensors at each section. Based on the monitoring results of each section, a distribution map of the blade bending moment is formed along the blade length direction, and the blade bending moment information is obtained through analysis.

[0037] Step 3: Under the same environmental conditions, wind speed, and turbine model, blade damage will reduce the wind turbine's rotational speed, thereby affecting the frequency of rotational noise. For turbulent inflow noise and airfoil self-excitation noise, sand holes and cracks on the blade will change the roughness of the blade surface, and wear damage on the leading and trailing edges will change the dimensions of the leading and trailing edges, change the blade chord length, and affect turbulent inflow noise. Damage also changes the form of the turbulent layer on the blade surface, alters the boundary layer noise, and disrupts the boundary layer separation conditions, affecting airfoil self-excitation noise.

[0038] Therefore, by analyzing the rotational noise feature information, the blade frequency information is obtained. Combined with the turbulent inflow noise feature information and the airfoil self-excitation noise feature information, the blade shape information and blade roughness information are obtained. Finally, the convolutional neural network is used to detect and identify image feature information to obtain the blade surface defect information.

[0039] Furthermore, by comparing the bending moments at the same cross-section of the three blades of the same wind turbine, the consistency of the blades is determined. The blade vibration information monitored by the MEMS fiber optic accelerometer is used as the standard. Based on the frequency change trend reflected by the monitored blade vibration information, it is determined whether there is a fault in the blade. Combined with the blade consistency information, it is determined whether the blade is in good operating condition, thereby obtaining blade operation fault information.

[0040] Step 4: The wind farm control center characterizes the blade failure mode by using blade frequency information, blade shape information, blade roughness information, blade surface defect information, and blade operation failure information.

[0041] Specifically, blade frequency information and corresponding blade operation fault information characterize the blade fault mode as sand holes and voids; blade shape information, blade roughness information and corresponding blade operation fault information characterize the corresponding blade fault mode as blade icing; blade surface defect information and corresponding blade operation fault information characterize the corresponding blade fault mode as surface cracks and surface fissures.

[0042] This embodiment also provides a fault mode characterization system for offshore wind turbine blades, including an information acquisition module, a feature information extraction module, a fault information analysis module, and a fault mode characterization module;

[0043] Specifically, the information acquisition module collects blade noise information, blade image information, blade load information, and blade acceleration information; the feature information extraction module extracts noise feature values ​​based on the blade noise information to obtain noise feature information; simultaneously, it preprocesses and extracts features from the blade image information to obtain image feature information; it analyzes the blade load information to obtain blade bending moment information, and analyzes the blade acceleration information to obtain blade vibration information; the fault information analysis module identifies blade structural fault information corresponding to different feature information through the noise feature information and image feature information; it compares multiple blade bending moment information to obtain blade consistency information, and then combines this with the blade vibration information to obtain blade operational fault information; the fault mode characterization module analyzes and characterizes blade fault modes based on the blade structural fault information and blade operational fault information.

[0044] The module division in this embodiment of the invention is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in the various embodiments of the invention can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0045] This embodiment also provides a computer device, which includes a processor and a memory. The memory stores a computer program, which includes program instructions. The processor executes the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to realize the corresponding method flow or corresponding function. The processor described in this embodiment can be used for the operation of the offshore wind turbine blade fault mode characterization method.

[0046] This embodiment also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, this storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the offshore wind turbine blade fault mode characterization method in the above embodiment.

[0047] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0049] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0050] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes. Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A method for characterizing the failure modes of offshore wind turbine blades, characterized in that, Includes the following steps: Collect blade noise information, blade image information, blade load information, and blade acceleration information; Based on the blade noise information, noise feature values ​​are extracted to obtain noise feature information; Simultaneously, feature extraction is performed on the blade image information to obtain image feature information; the blade load information is analyzed to obtain blade bending moment information, and the blade acceleration information is analyzed to obtain blade vibration information; By using the noise feature information and image feature information, the blade structure fault information corresponding to different feature information is identified; at the same time, based on multiple blade bending moment information, blade consistency information is obtained by comparison, and then combined with the blade vibration information, blade operation fault information is obtained; Based on the blade structural fault information and blade operational fault information, the blade fault modes are analyzed and characterized.

2. The method for characterizing the failure modes of offshore wind turbine blades according to claim 1, characterized in that, The blade noise information includes aerodynamic noise, mechanical noise, and electromagnetic noise.

3. The method for characterizing the failure modes of offshore wind turbine blades according to claim 2, characterized in that, After collecting the blade noise information, the blade noise information is filtered and denoised to remove the mechanical and electromagnetic noise.

4. The method for characterizing the failure modes of offshore wind turbine blades according to claim 1, characterized in that, The noise characteristic information includes: rotational noise characteristic information, turbulent inflow noise characteristic information, and airfoil self-excitation noise characteristic information.

5. The method for characterizing the failure modes of offshore wind turbine blades according to claim 4, characterized in that, The step of identifying blade structure fault information corresponding to different feature information using the noise feature information and image feature information specifically includes: Based on the rotational noise feature information, the blade frequency information is initially obtained through analysis. Then, combined with the turbulent inflow noise feature information and the airfoil self-excitation noise feature information, the blade shape information and blade roughness information are further obtained through analysis. At the same time, based on the image feature information, a convolutional neural network is used to perform target detection and recognition to obtain the blade surface defect information. Blade structural fault information includes: blade frequency information, blade shape information, blade roughness information, and blade surface defect information.

6. The method for characterizing the failure modes of offshore wind turbine blades according to claim 1, characterized in that, The step of obtaining blade consistency information by comparing multiple blade bending moment information and then combining the blade vibration information to obtain blade operation fault information specifically includes: Blade consistency information is obtained by comparing the blade bending moment information of three blades of the same wind turbine at the same cross section. Using the blade vibration information during normal blade operation as a standard, and based on the blade consistency information and blade vibration information, the first blade operation fault information, the second blade operation fault information, and the third blade operation fault information are obtained. The blade operation fault information includes the first blade operation fault information, the second blade operation fault information, and the third blade operation fault information.

7. The method for characterizing the failure modes of offshore wind turbine blades according to claim 1, characterized in that, The steps for analyzing and characterizing blade failure modes based on the blade structural failure information and blade operational failure information specifically include: Blade structural fault information includes: blade frequency information, blade shape information, blade roughness information, and blade surface defect information; Based on the blade frequency information and the corresponding blade operation fault information, the corresponding blade fault mode is characterized as sand hole and void. Based on the blade shape information, blade roughness information, and corresponding blade operation fault information, the corresponding blade fault mode is characterized as blade icing; Based on the blade surface defect information and the corresponding blade operation fault information, the corresponding blade fault mode is characterized as surface crack and surface fissure.

8. A fault mode characterization system for offshore wind turbine blades, characterized in that, include: The information acquisition module is used to collect blade noise information, blade image information, blade load information, and blade acceleration information; The feature information extraction module is used to extract noise feature values ​​based on the blade noise information to obtain noise feature information; Simultaneously, image feature information is obtained by preprocessing and feature extraction of the blade image information; blade bending moment information is obtained by analyzing the blade load information, and blade vibration information is obtained by analyzing the blade acceleration information. The fault information analysis module is used to identify blade structure fault information corresponding to different feature information through the noise feature information and image feature information; at the same time, it compares multiple blade bending moment information to obtain blade consistency information, and then combines the blade vibration information to obtain blade operation fault information. The fault mode characterization module is used to analyze and characterize the blade fault modes based on the blade structure fault information and blade operation fault information.

9. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable in the processor. When the processor executes the computer program, it implements the steps of the method for characterizing the failure modes of offshore wind turbine blades according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for characterizing the failure modes of offshore wind turbine blades as described in any one of claims 1 to 7.

Images