KR102119185B1 - Wood furniture production system - Google Patents

Abstract

The present invention relates to a furniture production system. The furniture production system includes: a purchase information collection unit collecting product purchase information for the production of customized furniture; a wood selecting unit for selecting at least one base member from base members made of wood based on the wood processing information linked to furniture product purchase information; a driving unit for generating a drive signal of at least one of a wood processing facility among a plurality of wood processing facilities on the basis of the selection result of the wood selecting unit and the furniture product purchase information; an image acquisition unit for acquiring image information of the furniture produced using a 3D measuring device; and a determination unit that determines whether the produced furniture is defective by using an artificial neural network which is constructed through learning and receives image information obtained from the image acquisition unit and outputs whether or not the produced furniture is defective.

Description

Furniture production system {WOOD FURNITURE PRODUCTION SYSTEM}

The present invention relates to a furniture manufacturing system.

In general, various materials such as wood, plastic, light metal, steel, bamboo, leather and cloth are used as materials mainly used for furniture. Wood is a wood material needed to produce architecture, furniture, boards, pulp, paper, etc., and means wood materials made in the required dimensions and shapes.

Furniture can be categorized in various ways, such as a table, shelf, sofa (chair), dining table, desk, bookcase, and wardrobe, and can be produced in various shapes depending on the materials used. Custom furniture can be produced in the shape (shape) desired by the user, and the material used for the furniture can also be selected as the material desired by the user.

In the production of furniture, a problem that a defect rate may occur, such as a finish, a non-smooth surface, or inconsistent color may occur when the machine is operated.

The background technology of the present application is disclosed in Korean Patent Publication No. 10-2005-0026323.

The present invention is to solve the problems of the above-described prior art, it is an object to provide a furniture production system capable of producing user-customized furniture by collecting product purchase information and selecting and recommending wood used for furniture production.

The present application is to solve the problems of the prior art described above, and collects image information to detect defects in the produced furniture, and uses artificial neural networks to produce furniture that can accurately detect areas that the user cannot see with the naked eye. The aim is to provide a system.

The present application is to solve the above-described problems of the prior art, by using a variety of sensors to sense the internal and external state of the reducer of the processing equipment used for furniture production, taking into account the driving information of a plurality of reducers provided in the machine , It is an object of the present invention to provide a furniture production system that can control a drive of a reducer included in each of a plurality of processing equipments and provide a solution to a cause of failure of the reducer.

However, the technical problems to be achieved by the embodiments of the present application are not limited to the technical problems as described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, the furniture production system according to an embodiment of the present application, a purchase information collection unit for collecting product purchase information for user-customized furniture production, wood linked to the furniture product purchase information Based on the processing information, at least one of a plurality of wood processing equipment on the basis of the wood selection unit for selecting at least one of the base member of the wood base member, the selection result of the wood selection unit and the furniture product purchase information A driving unit for generating a driving signal of a wood processing equipment, an image acquiring unit for acquiring image information of furniture produced using a 3D measuring device, and the image information acquired by the image acquiring unit as input and outputting whether or not it is defective It may include a determination unit for determining whether the produced furniture is defective by using an artificial neural network constructed through learning.

According to one embodiment of the present application, further comprising an external environmental information collecting unit for collecting environmental information provided with a wooden base member, wherein the wood selecting unit further comprises at least one of the wooden base members based on the external environmental information. Either base member can be selected.

According to the exemplary embodiment of the present application, a temperature control unit controlling at least one of the temperature control devices provided in the wood storage location based on the environment information of the external environment collection unit may be further included.

According to an embodiment of the present application, further comprising a wood state information detection unit for detecting the state information of the wood, the wood state information detection unit, if the base member made of wood is wood, cracks, knots, rots of the base member At least one of the defective information can be detected.

According to an embodiment of the present application, the determination unit determines whether the failure information of at least one of the cracks, knots, and rots of the base member detected by the wood condition information detection unit is greater than or equal to a threshold value, wherein the driving unit comprises: When the defect information determined by the determination unit is greater than or equal to a threshold, a driving signal of at least one wood processing equipment among a plurality of wood processing equipment may be generated.

According to one embodiment of the present application, the plurality of wood processing equipment may include hole processing equipment, sewing equipment, cutting equipment, adhesive equipment, assembly equipment, and polishing equipment.

According to an embodiment of the present application, including a performance determining unit for determining the performance of the furniture produced based on the predetermined criteria of the furniture, the performance determining unit, stability, static strength and durability, surface treatment, insulation resistance, withstand voltage , It is possible to determine the performance of at least one of the materials.

According to one embodiment of the present application, a price calculation unit may be further included to calculate a price based on the product purchase information and wood and parts information used for furniture.

According to one embodiment of the present application, further comprising an intelligent control reduction device for controlling at least one of the plurality of wood processing equipment wood processing equipment, the intelligent control reduction device, wood processing using a plurality of sensors Sensor unit for sensing the states of a plurality of reducers provided in the equipment, driving information of at least one of the plurality of reducers, and real-time sensor result data, maintenance history, replacement time for each of a plurality of parts included in the reducer And a collection unit for collecting maintenance data including at least one of failure history data, a generating unit for generating status information of the reduction gear based on the sensing information and the driving information, and the reduction gear operation in consideration of the state information of the reduction gear. It may include a control unit for generating a control signal to control.

According to one embodiment of the present application, the driving unit may control driving of the reduction gear based on a control signal generated by the control unit.

According to one embodiment of the present application, the control unit generates the control signals for controlling the operation of each of the reducers in consideration of the collected plurality of reducers and the driving information and the sensing information, wherein the driving unit generates the plurality of reducers The driving of each of the plurality of speed reducers may be controlled based on the control signal for each.

The above-described problem solving means are merely exemplary and should not be construed as limiting the present application. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-described problem solving means of the present application, it is possible to collect product purchase information and select and recommend wood used for furniture production to produce customized furniture.

The present application is intended to solve the problems of the prior art described above, and collects image information in order to detect defects in the produced furniture, and it is possible to accurately use an artificial neural network to an area that the user cannot visually confirm.

The present application is to solve the above-described problems of the prior art, by using a variety of sensors to sense the internal and external state of the reducer of the processing equipment used for furniture production, taking into account the driving information of a plurality of reducers provided in the machine , By controlling the operation of the reducer included in each of the plurality of processing equipment, it is possible to provide a furniture production system that can provide a solution to the cause of the failure of the reducer.

However, the effects obtainable herein are not limited to the above-described effects, and other effects may exist.

1 is a schematic system diagram of a furniture production system according to an embodiment of the present application.
2 is a schematic block diagram of a furniture production system according to an embodiment of the present application.
3 is a view for explaining the detection of wood condition information of a furniture production system according to an embodiment of the present application.
4 is a view for explaining a defect detection of a furniture production system according to an embodiment of the present application.
5 is a schematic block diagram of an intelligent control reduction device of a furniture production system according to an embodiment of the present application.
6 is a schematic configuration diagram of an intelligent control reduction device of a furniture production system according to an embodiment of the present application.

Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present application pertains may easily practice. However, the present application may be implemented in various different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present application in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Throughout this specification, when a part is "connected" to another part, it is not only "directly connected", but also "electrically connected" or "indirectly connected" with another element in between. "It also includes the case where it is.

Throughout the present specification, when a member is positioned on another member “on”, “on the top”, “top”, “bottom”, “bottom”, “bottom”, this means that one member is attached to another member. This includes cases where there is another member between the two members as well as when in contact.

Throughout this specification, when a part “includes” a certain component, it means that the component may further include other components, not to exclude other components, unless otherwise stated.

The furniture production system is for producing user-customized furniture, can recommend materials used for furniture production, can control the operation of processing equipment used for furniture production, and detects defects in the furniture produced. can do.

1 is a schematic system diagram of a furniture production system according to an embodiment of the present application.

Referring to FIG. 1, the furniture production system 10 may provide a product purchase information menu to the user terminal 30. For example, the user terminal 30 downloads and installs the application program provided by the furniture production system 10, and a product purchase information menu may be provided through the installed application.

According to one embodiment of the present application, the furniture production system 10 collects product purchase information for user-customized furniture production, and based on wood processing information linked to furniture product purchase information, at least any of the base members made of wood. One base member can be selected. In addition, the furniture production system 10 may generate a driving signal of at least one wood processing equipment among a plurality of wood processing equipment based on the selected base member and furniture product purchase information.

In addition, the furniture production system 10 may determine whether the final produced furniture image information is defective through learning to detect whether it is defective using the produced furniture image information.

In addition, the furniture production system 10 may generate a control signal for controlling a plurality of wood processing equipment, based on the state information of the wood processing equipment.

For example, the furniture production system 10 may transmit and receive data, contents, and various communication signals with the user terminal 30 through a network, and include all kinds of servers, terminals, or devices having functions of data storage and processing. Can be.

The user terminal 30 is a device interworking with the furniture production system 10 through a network, for example, a smartphone (Smartphone), a smart pad (Smart Pad), a tablet PC, a wearable device and the like PCS (Personal Communication System) , GSM (Global System for Mobile communication), PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, It may be any type of wireless communication devices such as W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) terminals, and fixed terminals such as desktop computers and smart TVs.

Examples of the network 40 for sharing information between the furniture production system 10 and the user terminal 30 are 3rd Generation Partnership Project (3GPP) network, Long Term Evolution (LTE) network, 5G network, World Interoperability for WIMAX Microwave Access (Network), wired and wireless Internet (LAN), Local Area Network (LAN), Wireless Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), Bluetooth network, Wifi network, An NFC (Near Field Communication) network, a satellite broadcasting network, an analog broadcasting network, and a Digital Multimedia Broadcasting (DMB) network may be included, but are not limited thereto.

2 is a schematic block diagram of a furniture production system according to an embodiment of the present application.

Referring to FIG. 2, the furniture production system 10 includes a purchase information collection unit 11, a wood selection unit 12, a driving unit 13, an image acquisition unit 14, a determination unit 15, and external environment information collection The unit 16 may include a wood condition information detection unit 17, a performance determination unit 18, and a price calculation unit 19. However, the configuration of the furniture production system 10 is not limited to this. For example, the furniture production system 10 may further include a database for storing collected data, an external server for receiving information necessary for furniture production, and the like.

According to one embodiment of the present application, the purchase information collection unit 11 may collect product purchase information for the production of user-customized furniture. The purchase information collection unit 11 may collect product purchase information from a user terminal (not shown). Product purchase information may include the type of furniture, product name, use, material, dimensions, etc. that the user intends to purchase. For example, the type of furniture may include a desk, chair, drawer, shelf, bookcase, and the like. Further, the product name of the furniture may be a product name of an existing produced product. In addition, the use of furniture may include things related to the use of furniture such as household, office, and school use. In addition, the dimensions of the furniture may be information including width, width, height, and the like when the user wants to produce custom furniture other than existing furniture products.

According to one embodiment of the present application, the purchase information collection unit 11 may provide a ready-made product information item to a user terminal (not shown). The user may select at least one of the ready-made product information items displayed on the user terminal (not shown). The purchase information collection unit 11 may collect product purchase information for custom furniture production based on user input information on a ready-made product information item provided to a user terminal (not shown). Here, the ready-made product information item may include the type of furniture, product name, use, material, dimensions, and the like. Ready-made products may mean previously produced furniture products.

According to one embodiment of the present application, the wood selector 12 may select at least one of the base members made of wood, based on wood processing information linked to furniture product purchase information. In one example, the wood processing information may include the width, length, and quantity of the base member. Further, the wood processing information may include the type of wood. For example, when the furniture product purchase information is an office desk, the wood selection unit 12 may select a base member made of wood, based on the wood processing information associated with the office desk information. For example, a wooden base member associated with office desk information may be a plywood member. The wood selection unit 12 may select at least one of a plurality of base members in consideration of the use purpose, size, and currently available base member of the furniture.

The rootstock of the tree or the entire tree is used, but the tree is usually used except in special cases. There are coniferous and hardwoods in wood, each with different components. The main ingredients are cellulose, hemicellulose, and lignin, and other minor ingredients are also included. The specific gravity varies depending on the species, but in general, the coniferous material ranges from 0.3 to 0.9 and the hardwood material ranges from 0.2 to 1.3. Under normal atmospheric conditions, it contains about 15 moisture, and swells and contracts according to moisture absorption and moisture absorption. Applications vary depending on the type of construction, furniture, packaging boxes, ships, vehicles, shafts, sleepers, electric poles, musical instruments, sports equipment, and plywood.

According to one embodiment of the present application, the wood selector 12 may select a base member in consideration of at least one of surface strength, fracture parameter, modulus of elasticity, compressive strength, and shrinkage. Here, the surface strength (Janka Hardness) represents the magnitude of the force that falls into the tree and falls half of the hole. The larger the surface strength, the better the surface strength, and the unit is pounds (lb). The modulus of rupture indicates how hard it is to break when applied to the center of the plate. The larger the fracture factor, the stronger the wood, and the unit is pounds per square inch (lb/square-inch). The modulus of elasticity indicates how well a tree bends, and the larger the value, the less bendable. A tree with a smaller value can be considered to be deflected without a support column when used as a shelf, and the unit is per square inch. It is pounds (lb / square-inch). Compressive strength (Crushing Strenght) indicates how much force is applied to break at both ends of the plate to break. The unit is pounds per square inch (lb/square-inch). The shrinkage (Shrinkage) indicates how much shrinkage occurs when the wood is dried compared to the living state, where R is the radial direction, T is the tangential direction, and V is the volume of shrinkage reflecting R and T, T /R is the ratio of shrinkage in the tangential direction to the radial direction.

Exemplary wooden base members include: Spruce (Sqruce), Radiata Pine (New Song), Red Pine (Scots Pine, Sasna), Elliot Pine (Slash Pine, Misong, Brazilian Song), May include solid wood members such as Western Red Cedar, Rubberwood, Merbau, Red Alder, Silver Birch, Ash, Ash, etc. . Specific properties of spruce: 0.41, surface strength = 377, fracture coefficient = 9,130, elastic modulus = 1,406,000, compressive strength = 5,150, shrinkage: R = 3.9%, T = 8.2%, V = 12.1%, T/R = 2.1 to be. Physical properties of radiata pine: specific gravity: 0.51, surface strength = 710, fracture modulus = 11,480, modulus of elasticity = 1,458,000, compressive strength = 6.030, shrinkage: R = 3.4%, T = 6.7%, V = 10.7%, T/R = 2.0. Properties of Red Pine, specific gravity: 0.55, surface strength = 540, fracture coefficient = 12.080, elastic modulus = 1,461,000, compressive strength = 6,020, shrinkage: R = 5.2%, T = 8.3%, V = 13.6 %, T/R = 1.6. The properties of Elliottine, specific gravity: 0.65, surface strength = 760, fracture coefficient = 16,300, elastic modulus = 1,980,000, compressive strength = 8,140, shrinkage: R = 5.4%, T = 7.6%, V = 12.1 %, T/ R = 1.4. Physical properties of red cedar, specific gravity: 0.37, surface strength = 350, fracture coefficient = 7,500, elastic modulus = 1,110,000, compressive strength = 4,560, shrinkage: R = 2.4%, T = 5.0%, V = 6.8%, T/R = 2.1. Physical properties of dead trees: specific gravity: 0.59, surface strength = 960, fracture coefficient = 10,420, elastic modulus = 1,314,000, compressive strength = 6,110, shrinkage: R = 2.3%, T = 5.1%, V = 7.5%, T/R = 2.2. The properties of Mulbau, specific gravity: 0.83, surface strength = 1,710, fracture coefficient = 20,700, elastic modulus = 2,465,000, compressive strength = 10,600, shrinkage: R = 2.7%, T = 4.6%, V = 7.8%, T/R = 1.7. Alder's physical properties are: specific gravity: 0.47, surface strength = 590, fracture coefficient = 9,800, elastic modulus = 1,380,000, compressive strength = 5,820, shrinkage: R = 4.4%, T = 7.3%, V = 12.6%, T/R = 1.7. The properties of the birch are: specific gravity: 0.66, surface strength = 1,210, fracture coefficient = 16,570, elastic modulus = 2,024,000. Ash physical properties are: specific gravity: 0.65, surface strength = 1,480, fracture coefficient = 15,020, elastic modulus = 1,785,000, compressive strength = 7,400, shrinkage: R = 5.7%, T = 9.6%, V = 15.3 %, T/R = 1.7.

In addition, the base member made of wood may include a plate material that is made to be easy to use by secondary processing of wood that is not pure wood. The plate material may include plywood, MDF, PB, aggregate wood, and the like. Here, the plywood is made by stacking a plurality of thin woods, and is bonded with a bond between them, and may include general plywood, pine needle plywood, paulownia plywood, own plywood, and the like.

However, it is not limited to the base member described above, and the base member made of wood may further include a wood member suitable for producing furniture.

In the wood base member described above, drying and processing are important, and the temperature and humidity of the space in which the member is provided are also important.

According to one embodiment of the present application, the external environment collection unit 16 may collect environmental information provided with a wooden base member. The environmental information provided with the wooden base member may be environmental information of the wood storage place. The wood storage place may be a place where one type of wood is provided. Further, the wood storage place may be a place where a plurality of types of wood is provided. The external environment collection unit 16 may collect the temperature, humidity, air condition, and concentration of dust (dust) in a wood storage place. The external environment collecting unit 16 may collect environmental information using a device capable of collecting temperature, humidity, air condition, and concentration of dust (dust).

According to one embodiment of the present application, the temperature control unit (not shown) may control at least one of the temperature control devices provided in the wood storage place based on the environmental information collected from the external environment collection unit 16. have. The temperature control device may include a device for adjusting temperature, humidity, air condition, concentration of dust (dust), and the like. The temperature control unit (not shown) may generate a control signal for controlling at least one of the temperature control devices and control the control device based on the type and environment information of the wood provided in the wood storage place. As an example, when the environmental information collected by the external environment collection unit 16 does not satisfy a preset condition, the temperature control unit (not shown) controls at least one of the temperature control devices provided in the wood storage place. can do. Since wood can be deformed during storage according to environmental information, by controlling the control device provided in the temperature control device provided in the wood storage place based on the information collected from the external environment collection unit 16, the wood is not deformed. Can be stored.

According to one embodiment of the present application, the wood selection unit 12 may select at least one member of a base member made of wood based on external environment information. For example, when the environmental information collected by the external environment collection unit 16 does not satisfy a preset condition, the wood selection unit 12 may select a base member made of wood that does not change in the external environment. That is, it is possible to produce furniture without defects by selecting a base member made of wood, except for wood, which may cause changes in external environmental information.

3 is a view for explaining the detection of wood condition information of a furniture production system according to an embodiment of the present application.

According to one embodiment of the present application, the wood condition information detection unit 17 may detect the state information of the wood. The wood state information detector 17 may collect wood state information using an image acquisition device or the like. For example, the wood condition information detection unit 17 detects at least one of the defect information (1) among cracks, knots, and rots of the base member (for example, wood) when the base member made of wood is solid wood. Can be. For example, the wood condition information detection unit 17 based on the state information of the wood collected by the image acquisition device, the presence or absence of a different shape (shape) from other areas, based on the contrast information, the defect information in the base member made of wood Can be detected.

Further, the determination unit 15 may determine whether at least one of the crack information, the knot, and the rottenness of the base member detected by the wood condition information detection unit 17 is greater than or equal to a threshold value. The driving unit 13 may generate a driving signal of at least one wood processing equipment among a plurality of wood processing equipment when the defect information determined by the determination unit 15 is greater than or equal to a threshold. For example, referring to FIG. 3, when the defective information determined by the determining unit 15 is greater than or equal to a threshold value, the driving unit 13 performs additional process processing on the region 1 of the base member where the defective information is detected. , It can generate the driving signal of the wood processing equipment.

Exemplarily, referring to FIG. 3, the determination unit 15 uses the defect information 1 in the first area of the wood detected by the wood condition detection unit 17 to determine the defect information 1 in the first area. It is possible to determine if is greater than or equal to the threshold. The driving unit 13 may generate a driving signal for driving the polishing equipment among the plurality of wood processing equipment when the defect information determined by the determination unit 15 is greater than or equal to a threshold.

According to one embodiment of the present application, the driving unit 13 may generate a driving signal of at least one of wood processing equipment among a plurality of wood processing equipment based on the selection result of the wood selection unit 12 and furniture product purchase information. have. For example, the plurality of wood processing equipment may include, but is not limited to, hole processing equipment, sewing equipment, cutting equipment, bonding equipment, assembly equipment, polishing equipment, and the like. For example, the driving unit 13 may generate a driving signal for driving the first wood processing equipment among wood processing equipment based on the characteristics of the base member selected by the wood selection unit 12. When the base member selected by the wood selection unit 12 is the first wood, the driving unit 13 may generate a driving signal for driving the first wood processing equipment suitable for the first wood. For example, the driving unit 13 may generate a driving signal of the second wood processing equipment among the plurality of wood processing equipment based on the dimension information among furniture product purchase information. The driving unit 13 may generate a driving signal of at least one wood processing equipment among a plurality of wood processing equipment to cut and process wood used for furniture.

For example, in the driving unit 13, the selection result of the wood selection unit 12 is the first wood (for example, plywood), and the furniture product purchase information is the first information (for example, a ready-made office desk). In this case, a driving signal of a hole processing equipment, a cutting equipment, and an assembly equipment among a plurality of wood processing equipments may be generated based on the corresponding information. The driving unit 13 may generate a driving signal that allows the hole processing equipment to process holes of 3 cm in diameter in the first and second areas of the first wood. In addition, when the selection result of the wood selection unit 12 is the first wood (for example, plywood) and the furniture product purchase information is the first information (for example, a ready-made office desk), the driving unit 13 Based on the dimension information included in the furniture product purchase information, a driving signal of the cutting equipment may be generated so that the first wood is cut according to the corresponding dimension.

According to an embodiment of the present application, the image acquisition unit 14 may acquire image information of furniture produced using a 3D measuring device. A three-dimensional measuring machine is a device that measures the dimensions and shape of a workpiece by using the coordinate direction of the measuring machine as the X axis, the front and rear direction as the Y axis, and the vertical direction as the Z axis. When the probe is brought into contact with the measuring surface, information on one point is measured simultaneously on three axes, and is connected to a microcomputer or the like to perform high-precision or rapid data processing for storage. Objects with many measurement points and complex shapes are more effective, and measurement of a free-form surface or the like, which has been extremely difficult to measure, has been facilitated. In addition, the image acquiring unit 14 may acquire image information of the furniture produced by using the photographing device or the like of the finally produced furniture. At this time, the image acquisition unit 14 may acquire image information including the overall shape of the furniture, such as front, back, top, left, and right sides. The image acquisition unit 14 may preprocess to include only the produced furniture image. For example, the image acquisition unit 14 may acquire image information from which the image information background of furniture is removed. Also, the image acquisition unit 14 may exclude the corresponding image when an image having a low or low quality, such as out-of-focus or transliteration, is acquired during the image acquisition process. In other words, if the image is not applicable to the deep learning algorithm, the image acquisition unit 14 may exclude the corresponding image.

4 is a view for explaining a defect detection of a furniture production system according to an embodiment of the present application.

According to one embodiment of the present application, the determination unit 15 is a defect in furniture produced using an artificial neural network constructed through learning that inputs image information obtained from the image acquisition unit 14 and outputs whether it is defective or not. Can determine whether The determination unit 15 may generate a learning data set and a verification data set for applying an artificial neural network (deep learning algorithm). A data set may be generated by classifying the data set into a training data set required for learning an artificial neural network and a verification data set for verifying progress information of learning of an artificial neural network. As an example, the determination unit 15 may classify an image to be used for a learning data set and an image to be used for a verification data set randomly among image information of the produced furniture obtained from the image acquisition unit 14. In addition, the determination unit 15 may select the data set for verification and use the remaining data set as a training data set. The data set for verification can be randomly selected. The ratio of the verification data set and the learning data set may be determined by a preset reference value. In this case, the preset reference value may be set as 10% of the data set for verification and 90% of the data set for learning, but is not limited thereto. In this case, the verification data set may be a data set that does not overlap with the learning data set. Since the data for verification is data that has not been used for the construction of an artificial neural network, it is the first data encountered in the artificial neural network at the time of verification. Therefore, the data set for verification may be a data set suitable for evaluating the performance of the artificial neural network when a new image (a new image not used for learning) is input.

According to one embodiment of the present application, the determination unit 15 may determine whether the furniture produced is defective by using convolutional neural networks. A synthetic neural network is a type of neural network mainly used in speech recognition or image recognition. It is configured to process multidimensional array data, and is specialized in multidimensional array processing such as color images. The composite neural network divides and processes the image into multiple pieces rather than a single piece of data, so that even if the image is distorted, it is possible to extract partial characteristics of the image, thereby achieving correct performance.

For example, referring to FIG. 4, the determination unit 15 inputs the existing image information ((a) of FIG. 4) and the image information (b) obtained from the image acquisition unit 14 as inputs and determines whether it is defective. Using the artificial neural network constructed through learning as an output, it is possible to determine whether the furniture produced is defective. The reference image information may be a determined image based on a result determined by the determination unit 15 as a household in which a defect is not detected, and determined by the user with the naked eye.

According to one embodiment of the present application, the performance determining unit 18 may determine the performance of the furniture produced based on a predetermined criterion for determining furniture. For example, when the produced furniture is the storage furniture, the performance determining unit 18 may determine the performance of the furniture produced based on the items included in the stability a. The items included in stability a may include stability without applying force, and stability (vertical force) when a force is applied to the movable part. In addition, the performance determination unit 18 may determine the performance of the furniture produced based on items included in static strength and durability. Items included in static strength and durability may include performance evaluation items regarding the strength b of the shelf support, and no breakage, deformation, and mismatch in use. In addition, the items included in the static strength and durability should be less than or equal to 0.5% of the warpage c and the amount of warpage (when loaded), and may include performance evaluation items regarding that there will be no disruptive damage and deformation in use. Also, the performance determining unit 18 may determine the performance of the furniture produced based on the items included in the surface treatment h. The items included in the surface treatment h may include wood and metal coating films, and it may be determined that the wood and metal coatings are not peeled off. In addition, the performance determining unit 18 may determine the insulation resistance and withstand voltage items. The insulation resistance performance is 1 M1 or more, and the performance of withstanding voltage resistance can be judged. In addition, the performance determining unit 18 may determine performance of items included in materials, plywood, particle board, and fiber board. When the material is wood, the water content (%) is 12 or less, and plywood, particleboard, and fiberboard formaldehyde emission (mg/L) can be judged as to whether the average is 0.5 or less and up to 0.7 or less. The determination items of the performance determination unit 18 described above are illustrated, for example, in the storage furniture, but preset items are different depending on the furniture to be produced.

According to one embodiment of the present application, the price calculator 19 may calculate a price based on product purchase information and wood and parts information used in furniture. For example, the price calculating unit 19 may calculate the price of furniture produced based on the type of wood, the type of parts, the dimension information included in the product purchase information, the type of furniture, and the like. The price calculating unit 19 may calculate the produced price in consideration of the reference price of wood, the reference price of parts included in the produced furniture, and the product price requested by the user. The price calculating unit 19 may calculate the final price of the corresponding product based on the product price that can be changed according to the state information of the used wood, even if it is a ready-made product. The price calculating unit 19 may calculate the price of a fairer product by providing the calculated price product to the buyer terminal and the producer terminal.

5 is a schematic block diagram of an intelligent control deceleration device of a furniture production system according to an embodiment of the present application, and FIG. 6 is a schematic block diagram of an intelligent control deceleration device of a furniture production system according to an embodiment of the present application.

Referring to FIG. 5, the intelligent control reduction device 20 may include a sensor unit 21, a collection unit 22, a generation unit 23, and a control unit 24. However, the intelligent control reduction device 20 is not limited thereto. For example, the intelligent control deceleration device 20 may include a provision unit (not shown) that provides the generated maintenance data to the user terminal 30.

According to one embodiment of the present application, the sensor unit 21 may sense the states of the reducers 2 and 3 using a plurality of sensors. The sensor unit 21 may detect the internal and external states of the reducers 2 and 3 using a plurality of sensors. For example, the plurality of sensors may include temperature, speed, tilt, angle, geomagnetism, and sensing sensors. The sensor unit 21 may detect the temperature of the reducer by using a temperature sensor to check whether the reducers 2 and 3 generate heat. Further, the sensor unit 21 may sense the deceleration degree (fast) of the decelerator using a speed sensor in order to sense the deceleration degree of the decelerator. In addition, the sensor unit 21 can monitor the under or excessive, poor or inappropriate of the lubricant. In addition, the sensor unit 21 may include a sensor for checking the state of the bearing. In addition, the sensor unit 21 may include a sensor for acquiring tooth wear, foreign matter intrusion, bearing wear and damage, balance information of the shaft center, etc., which cause severe vibration, but the example described above is only an example and is limited to this. It is not intended that various embodiments may exist.

The collection unit 22 may collect driving information of at least one of the plurality of reducers 10 and 20. Referring to FIG. 2 as an example, the plurality of reducers 10 and 20 may be reducers 2 and 3 provided in wood processing equipment. The reducer is a mechanism that reduces the speed. It is a mechanism that converts the speed using a gear. It reduces the number of revolutions of the main drive source (mainly the motor) to the required number of revolutions to obtain higher torque (torque, force). It is made to.

For example, the wood processing equipment may include a plurality of processing equipment used while processing wood, such as a light boring machine, a metal cutting machine, a torch edge, a cutting machine, a cutting machine, and a point boring machine. The wood processing equipment described above is merely an example, and more various processing equipment may be included in the wood processing equipment.

The drive information includes speed information of the reducer, lube oil information, oil information, oil seal information, ventilation information, voltage information, bearing information, tooth pressure status information, tooth wear information, foreign substance intrusion information, shaft center information, case and joint damage information, packing (Joint) It may include information related to the operation of the reducer, such as defect information, fuse information, coil information, power information.

The collecting unit 22 may collect driving information of each of the reducers 2 and 3 provided in a single machine and provide them to the generating unit 23. The collection unit 22 may collect driving information related to driving of the reduction gear from at least one of the reduction gears provided with the machine.

The generator 23 may generate state information of the reducer based on the sensing information and the driving information. For example, the state information may include a fever state, a severe noise and joint state, a severe vibration state, an oil leakage state, a motor inability to start or a difficulty in starting. The generator 23 may classify and generate state information of the reducer in consideration of sensing information and driving information.

When information included in a preset reference value is received from the sensor unit 21 and the collection unit 22, the generation unit 23 may generate state information of the reducer in consideration of sensing information and driving information. The generation unit 23 may classify sensing information and driving information corresponding to the classified state information, and generate state information of the corresponding reducer.

Exemplary heating conditions include overloading of the reducer, under or over-lubricating oil, poor or inadequate lubrication, poor oil seal, impede airflow in the motor, short stator coils between layers, unbalanced voltage, bent shafts or tension in connections It may include state information such as the tight state, defective bearings (abrasion, roughness), forced assembly of the bearing parts, and friction of parts.

In addition, in severe noise and joint conditions, regular sinter-tooth densities, bearing damage, high metal noise-lack of lubricant, irregular noise-foreign matter intrusion, bearing damage, contact between rotor and stator, loosening of the fixed part (axis And gears, flange joints).

In addition, severe vibration conditions include tooth wear, foreign matter intrusion, bearing wear and damage, loosening of mounting bolts and fixed bolts, loosening of assembly parts (shafts, gears), axial center is not straight (bad balance), case and connection It may include status information such as site damage.

In addition, the oil leakage state may include state information such as oil seal damage, defective packing (joint part), drain plug loosening, oil level breakage and relaxation, other leaking welding parts, and output shaft wear (sealing area).

In addition, the motor start-up or start-up state may include state information such as a fuse being disconnected, a starting torque is insufficient, a coil is disconnected, a power failure or a power failure, an overload, a bearing or component jamming.

According to one embodiment of the present application, the controller 24 may generate a control signal for controlling the operation of the reducer in consideration of the state information of the reducer. For example, when the state information of the reducer generated by the generation unit 23 corresponds to the heat generation state information, the control unit 24 may generate a control signal that controls the operation of the reducer corresponding to the heat generation state. The control signal corresponding to the heating condition induces to adjust the load of the reducer or replace it with a large capacity, check the oil gauge, replace it with a new oil, replace the oil seal, control disturbances, request repair, inspect transformers and circuits, check the shaft and tension Control signals can be generated for adjustments, bearing replacements, overhaul checks, and correction requests.

In addition, the control unit 24, if the state information corresponds to a severe noise and joint state, gear replacement, bearing replacement, lubrication oil replenishment, foreign matter removal (washing), bearing replacement, repair request, inspection after disassembly, cause control, replacement request It is possible to generate a control signal for the back.

In addition, the control unit 24, when the status information corresponds to a severe vibration, gear replacement, foreign matter removal and lubricant replacement, bearing replacement, bolt tightening, reassembly after disassembly and inspection, connection status of the load and reconnection, replacement, etc. Control signals can be generated.

In addition, the control unit 24, when the status information corresponds to the leakage of oil, oil seal replacement, packing replacement and resealing, tightening tightly (Teflon tape), request to replace the oil gauge, rewelding or replacement of the welding part, replacement of the output shaft, etc. Control signal.

In addition, the control unit 24, if the status information corresponds to the motor start-up inability or start-up difficulty, fuse capacity check, replacement, start-up replacement or capacity increase, coil repair, power check, current measurement and load check, bearing Control signals for reassembly or replacement can be generated. The control unit 24 may generate a control signal for controlling driving of the reduction gear in response to each cause of the state information.

According to one embodiment of the present application, the driving unit 13 may control driving of the reduction gear based on a control signal. For example, when a control signal for stopping the reduction gear is received from the control unit 24, the driving unit 13 may stop driving the reduction gear. In addition, the driving unit 13 may receive control signals related to the deceleration speed, timing, accuracy, pattern, etc. of the reducer from the control unit 24 and control driving of the reducer.

According to one embodiment of the present application, the collection unit 24 may collect maintenance data for each of a plurality of parts of the reducer. The generation unit 23 may generate maintenance data of a plurality of parts based on the maintenance data of the collection unit 22. The plurality of parts may include bearings, coils, bolts, packings, engines, oils, lubricants, gears, and the like included in the reduction gear. The maintenance data may include at least one of real-time sensor result data, maintenance history, replacement time, and failure history data of each of the plurality of parts. The real-time sensor result data of the equipment may be result data collected from the sensor unit 21 provided outside the equipment. In addition, the collection unit 22 may collect maintenance data including replacement items of each component (part) required for the reducer, replacement date, replacement cycle, and aging speed of parts based on the environment.

Further, for example, maintenance data for each of the plurality of parts of the reducer may be data related to a failure and maintenance history of past equipment. The collection unit 22 may collect maintenance data by configuring maintenance data sets by connecting maintenance data for each of the parts through a database. In addition, the collection unit 22 may collect maintenance data from an external server through a network. At this time, the maintenance data may be data collected based on information received from the user terminal for maintenance history for each of a plurality of parts of the reducer.

The control unit 24 may generate a control signal that controls the operation of at least one of the plurality of reducers based on the generated maintenance data. For example, when abnormal information (for example, a replacement request due to aging of an accessory part) is collected from the maintenance data of the first reduction gear 3 among the plurality of reduction gears 3 and 4, the control unit 24 controls the second The reducer 4 may generate a control signal to be driven so that there is no problem in machine operation on behalf of the first reducer 3.

According to one embodiment of the present application, the intelligent control reduction device 20 may update the maintenance prediction model of the equipment through machine learning using maintenance data. In addition, the intelligent control reduction device 20 may apply a plurality of machine learning algorithms to perform learning on the generated maintenance prediction model. In other words, the maintenance prediction model generated by the intelligent control reduction device 20 may be trained by applying a plurality of machine learning algorithms. In addition, the intelligent control reduction device 20 may predict a failure of the equipment as a result of applying the machine learning algorithm to each of the plurality of machine learning algorithms by applying the generated maintenance prediction model to each of the plurality of machine learning algorithms.

According to one embodiment of the present application, the providing unit (not shown) may provide the generated maintenance data to the user terminal 30. In addition, the providing unit (not shown) may provide driving information of the plurality of reducers collected by the collecting unit 22 and status information generated by the generating unit 23 to the user terminal 30. For example, the user may provide the corresponding control input information to the generating unit 23 through the user terminal control input information for controlling the reducer based on the sensing information, driving information, and status information displayed on the user terminal. The generation unit 23 may generate status information based on user control input information, sensing information, and driving information received from the user terminal 30. The control unit 24 may generate a control signal for controlling the operation of at least one of the plurality of reducers using the generated state information, and when there is only one reducer included in the machine, the control unit 24 may It is possible to generate a control signal for controlling the driving of the included reducer.

6 is a schematic configuration diagram of an intelligent control reduction device of a furniture production system according to an embodiment of the present application.

Referring to FIG. 6, an exemplary embodiment will be described in which an intelligent control reduction device 20 controls a plurality of reduction devices 20 and 20' provided in a machine. In one embodiment of the present application, the machine 1 may be a conveyor belt. The machine (conveyor belt) may be provided with a first reducer 3 and a second reducer 4, and a plurality of reducers included in the machine based on control signals generated by sensing and collecting information from a plurality of reducers The reducer can be driven.

The foregoing description of the present application is for illustration, and a person having ordinary knowledge in the technical field to which the present application belongs will understand that it is possible to easily change to other specific forms without changing the technical spirit or essential characteristics of the present application. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present application is indicated by the claims below, rather than the detailed description, and it should be interpreted that all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof are included in the scope of the present application.

10: Furniture production system
11: Purchase information collection department
12: Wood selection
13: driving unit
14: image acquisition unit
15: judgment unit
16: External environmental information collection department
17: wood condition information detection unit
18: performance judgment unit
19: price calculator
20: intelligent control reduction gear
21: sensor unit
22: Collection
23: generation unit
24: control

Claims (11)

In the furniture production system,
A purchase information collection unit for collecting product purchase information for user-customized furniture production;
A wood selection unit for selecting at least one base member from among wood base members based on wood processing information linked to the product purchase information;
A driving unit generating a driving signal of at least one of wood processing equipment among a plurality of wood processing equipment based on the selection result of the wood selection unit and the furniture product purchase information;
An image acquiring unit that acquires image information of furniture produced using a 3D measuring device;
A determination unit that determines whether the produced furniture is defective by using an artificial neural network constructed through learning to input the image information obtained from the image acquisition unit as an input and outputs whether it is defective;
An external environmental information collection unit for collecting environmental information provided with a wooden base member;
When the environmental information collected by the external environment collection unit does not satisfy a preset condition, a temperature control unit controlling at least one of the temperature control devices provided in the wood storage place; And
Wood state information detection unit for detecting the state information of the wood using the image acquisition device,
Including,
The wood selector,
It is to select at least one base member of the base member made of wood based on at least one of the environmental information and the surface strength, fracture parameter, elastic modulus, compressive strength, and shrinkage of the wood,
The wood condition information detection unit,
When the base member made of wood is solid wood, at least one of the crack information, cracking, and rottenness of the base member is detected. Defect of the base member made of wood is detected based on the presence or absence of different shapes of regions and contrast information,
The determination unit,
It is determined that the defect information of at least one of the cracks, knots, and rots of the base member detected by the wood condition information detector is greater than or equal to a threshold,
Based on the image information of the generated furniture obtained from the image acquisition unit based on a preset reference value, the image to be used for the learning data set and the image to be used for the verification data set are classified, and the artificial neural network is used by using the verification data set Evaluate the performance of,
The driving unit,
When the defect information determined by the determination unit is greater than or equal to a threshold, a driving signal for at least one wood processing equipment among a plurality of wood processing equipment is generated. delete delete delete delete According to claim 1,
The plurality of wood processing equipment,
Furniture production system, including hole processing equipment, sewing equipment, cutting equipment, adhesive equipment, assembly equipment, polishing equipment. According to claim 1,
It includes a performance determining unit for determining the performance of the furniture produced based on the predetermined criteria of the furniture,
The performance determination unit,
Furniture production system to judge the performance of at least one of stability, static strength and durability, surface treatment, insulation resistance, withstand voltage, and material. According to claim 1,
Further comprising a price calculation unit for calculating a price based on the product purchase information and wood and parts information used in furniture, furniture production system. According to claim 1,
Further comprising an intelligent control reduction device for controlling at least one of the plurality of wood processing equipment wood processing equipment,
The intelligent control reduction device,
A sensor unit for sensing states of a plurality of reducers provided in a wood processing equipment using a plurality of sensors;
Collect maintenance data including at least one of driving information of at least one of the plurality of reducers and real-time sensor result data, maintenance history, replacement time, and failure history data for each of a plurality of parts included in the reducer. Collecting unit;
A generating unit generating state information of the reducer based on the sensing information and the driving information; And
Control unit for generating a control signal for controlling the operation of the reducer in consideration of the state information of the reducer
It includes, furniture production system. The method of claim 9,
The driving unit
Based on the control signal generated by the control unit, to control the driving of the reduction gear, furniture production system. The method of claim 10,
The control unit generates the control signals for controlling the operation of each of the reducers in consideration of the collected plurality of reducer drive information and the sensing information,
The drive unit controls the driving of each of the plurality of reducers based on the control signal for each of the generated plurality of reducers, furniture production system.

Images