KR20200095980A - Washing machine and Method for controlling the same - Google Patents

Abstract

The present invention relates to a washing machine and a control method of the washing machine. The washing machine according to an embodiment of the present invention includes: a washing tub that accommodates a cloth and is provided to be rotatable; a motor that rotates the washing tub; and a control unit that controls the motor to rotate the washing tub, wherein the control unit measures a plurality types of preset data while the washing tub accelerates from a first rotation speed to a second rotation speed faster than the first rotation speed, inputs the plurality types of data as input values of a previously trained artificial neural network, calculates a UB pattern expected in the future as a result value, and controls the motor to rotate the washing tub in a preset method based on the calculated type of the UB pattern.

Description

Washing machine and method for controlling the same

The present invention relates to a washing machine and a washing machine control method, and more particularly, to a washing machine and a washing machine control method capable of performing machine learning based fabric dispersion.

In general, a washing machine is a device for separating contaminants from laundry (hereinafter, also referred to as'po'), such as clothes and bedding, using chemical decomposition of water and detergent and physical action such as friction between water and laundry. It is collectively called.

Washing machines are largely divided into agitated and vortex and drum type washing machines. Among them, the drum-type washing machine includes a storage tank (or tub) containing water, and a washing tank (or drum) rotatably provided in the storage tank to accommodate laundry.

A plurality of through holes through which water passes are formed in the washing tank (or drum). The washing operation is generally divided into a washing administration, a rinsing administration and a dehydration administration. The process of such a stroke can be confirmed through a control panel (or display) provided outside the washing machine.

The laundry administration removes contaminants from the laundry by the friction between the water stored in the reservoir and the fabric stored in the laundry tank and the chemical action of the detergent stored in the water.

The rinsing process is to rinse the fabric by supplying water in which the detergent is not dissolved into the water storage tank. In particular, the detergent absorbed (or buried) in the fabric during washing is removed. During the rinse cycle, a fabric softener may be supplied with water.

The spin-drying cycle is to spin the cloth at high speed after the rinse cycle is completed. Normally, when the dehydration process is completed, all operations of the washing machine are ended. On the other hand, in the case of a combined drying washing machine, a drying cycle may be added after the spin-drying cycle.

Normally, the washing operation is set to operate under different conditions according to the amount of laundry (hereinafter, also referred to as'package') introduced into the washing tank. For example, settings such as water supply level, washing intensity, drainage time, and dehydration time may vary depending on the amount of cloth.

On the other hand, the laundry performance varies depending on the amount of laundry as well as the type of laundry (hereinafter, also referred to as'foaming'). When setting the laundry operation, when considering only the quantity, there is a problem that sufficient laundry performance cannot be expected. have.

On the other hand, it is necessary to effectively disperse the fabric in the dehydrating stroke after the washing stroke and the rinsing stroke are completed in the washing operation. If the fabric is not evenly distributed and is driven to either side, UB (Unbalance) is generated, and the shaking of the washing tank becomes large, and accordingly, the dehydration stroke time becomes longer and noise increases.

To this end, in the dehydration process, the process of dispersing the cloth is carried out, and various technologies have been developed to ensure proper and even distribution of the cell.

Meanwhile, in recent years, interest in machine learning such as artificial intelligence and deep learning has increased significantly.

Conventional machine learning is centered on statistical-based classification, regression, and cluster models. In particular, in supervised learning of classification and regression models, humans have previously defined a learning model to distinguish new data based on the characteristics of the training data. In contrast, deep learning is where computers find and discriminate features themselves.

One of the factors that has accelerated the development of deep learning is the deep learning framework provided as open source. For example, deep learning frameworks include Theano at Montreal University in Canada, Torch at New York University in the United States, Caffe at Berkeley University in California, and TensorFlow at Google.

With the release of deep learning frameworks, in addition to deep learning algorithms, extraction and selection of data used for learning, learning processes, and learning data are becoming more important for effective learning and recognition.

In addition, research to use artificial intelligence and machine learning for various products and services is increasing.

In addition, development to perform optimized dehydration strokes by applying artificial intelligence and machine learning to dehydration strokes is actively underway.

In order to solve the above problems, an embodiment of the present invention has an object to provide a washing machine and a washing machine control method capable of performing optimized fabric dispersion.

In addition, an embodiment of the present invention has an object to provide a washing machine and a washing machine control method capable of shortening the dehydration administration time.

In addition, an embodiment of the present invention is to provide a washing machine and a washing machine control method capable of preventing a delay in dehydration stroke time by extending a section for performing fabric dispersion by applying an artificial neural network learned by machine learning. have.

The problems of the present invention are not limited to the problems mentioned above, and other problems that are not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, the washing machine according to the embodiment of the present invention includes a washing tank that accommodates a cloth and is rotatably provided, a motor that rotates the washing tank, and a control unit that controls the motor to rotate the washing tank, The control unit measures a plurality of preset data while the washing tank accelerates from a first rotation speed to a second rotation speed that is faster than the first rotation speed, and inputs the artificial neural network that has learned the plurality of types of data. It is characterized in that the motor is controlled so that the washing tub is rotated in a preset manner based on the type of the calculated UB pattern, by inputting a value and calculating the expected UB pattern in the future.

In an embodiment, in the maintenance section in which the washing tank maintains rotation at the first rotational speed and in the acceleration section in which the washing tank accelerates from the first rotational speed to the second rotational speed, the cloth rises to a predetermined height and then falls. It characterized in that the dispersion is carried out by doing.

In an embodiment, until the rotational speed of the washing tub reaches the second rotational speed, the cloth is dispersed, and when the rotational speed of the washing tub reaches the second rotational speed, the cloth is It is attached and rotated, and the fabric dispersion is not performed.

In an embodiment, the plurality of types of data includes an average value of a UB value for a predetermined time, an average value of a rotational speed value of a washing tank for a predetermined time, an average value of a current value applied to the motor for a predetermined time, and vibration for a predetermined time. It characterized in that it comprises at least one of the average value of the vibration value measured by the sensor.

In an embodiment, the control unit is characterized in that the washing tank measures the plurality of types of data every predetermined time in an acceleration section that accelerates from the first rotational speed to the second rotational speed.

In an embodiment, the control unit measures the plurality of types of data every predetermined time, and based on the type of the UB pattern calculated through the artificial neural network using the measured plurality of types of data, the It is characterized by determining whether to accelerate, decelerate, or maintain the rotational speed of the washing tank.

In an embodiment, the calculated UB pattern includes a UB increase pattern expected to increase the UB value, a UB maintenance pattern expected to maintain the UB value, and a UB decrease pattern expected to decrease the UB value. It is characterized by.

In an embodiment, when the calculated UB pattern is a UB increase pattern in which the UB value is expected to increase, the control unit may reduce the rotation speed of the washing tub.

In an embodiment, the control unit is characterized in that when the calculated UB pattern is a UB reduction pattern that is expected to decrease the UB value, the rotation speed of the washing tank is increased.

In an embodiment, when the calculated UB pattern is a UB holding pattern that is expected to maintain a UB value, the controller maintains the rotation speed of the washing tub.

In an embodiment, when the UB value measured in an acceleration section in which the washing tank accelerates from the first rotational speed to the second rotational speed exceeds a reference value, the control unit shortens the rotation of the washing tank. do.

In an embodiment, the control unit short-circuits the rotation of the washing tank when the second washing speed is not reached within a preset time from the time when the washing tank starts to accelerate from the first rotation speed to the second rotation speed. It is characterized by letting.

A control method of a washing machine according to an embodiment of the present invention includes measuring a plurality of preset data while the washing tub accelerates from a first rotation speed to a second rotation speed faster than the first rotation speed, and the plurality of types Entering the data of the pre-trained artificial neural network as an input value, calculating a predicted UB pattern as a result value, and based on the calculated type of the UB pattern, the motor is configured to rotate the washing tank in a preset manner. And controlling.

In an embodiment, the calculated UB pattern includes a UB increase pattern expected to increase the UB value, a UB maintenance pattern expected to maintain the UB value, and a UB decrease pattern expected to decrease the UB value. It is characterized by.

In an embodiment, the controlling step is characterized in that when the calculated UB pattern is an UB increase pattern expected to increase the UB value, the rotation speed of the washing tank is decelerated.

In an embodiment, the controlling step is characterized in that when the calculated UB pattern is a UB reduction pattern expected to decrease the UB value, the rotation speed of the washing tank is increased.

In an embodiment, the controlling step is characterized in that when the calculated UB pattern is a UB holding pattern expected to maintain the UB value, the rotation speed of the washing tank is maintained.

Specific details of other embodiments are included in the detailed description and drawings.

According to an embodiment of the present invention, one or more of the following effects are provided.

First, according to the present invention, the cloth is distributed in the acceleration section that accelerates to the second rotational speed faster than the first rotational speed from the first rotational speed, as well as the maintenance section where the washing tank maintains rotation at the first rotational speed Optimized fabric dispersion can be performed by widening the section where dispersion is performed, and this has the effect of reducing the dehydration stroke time.

Second, the present invention accelerates the rotational speed of the washing tank based on the UB pattern predicted in the future by using the artificial neural network learned through machine learning in an acceleration section that accelerates from the first rotational speed to the second rotational speed. In addition to maintaining and decelerating the control, the dehydration stroke time can be significantly reduced by reducing the number of times the dehydration stroke is short-circuited.

Third, the present invention determines a method of controlling the rotational speed of the washing tub by using a plurality of types of data measured for a predetermined time, not one type of data measured at a certain moment, so that one measured data is In the case of an error value, there is an effect that it is possible to prevent the dehydration stroke time from being delayed by shorting the dehydration stroke.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

1 is a side cross-sectional view of a washing machine according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a control relationship between main components of the washing machine of FIG. 1.
3 is a view for explaining a conventional dehydration process.
4 is a view for explaining a dehydration stroke process according to an embodiment of the present invention.
5 is a flowchart illustrating a typical control method of the present invention.
6, 7 and 8 are conceptual diagrams illustrating the control method described in FIG. 5.

Hereinafter, exemplary embodiments disclosed in the present specification will be described in detail with reference to the accompanying drawings, but identical or similar elements are denoted by the same reference numerals regardless of reference numerals, and redundant descriptions thereof will be omitted. The suffixes "modules" and "parts" for components used in the following description are given or mixed only considering the ease of writing the specification, and do not have meanings or roles distinguished from each other in themselves. In addition, in the description of the embodiments disclosed herein, when it is determined that detailed descriptions of related known technologies may obscure the gist of the embodiments disclosed herein, detailed descriptions thereof will be omitted. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in the present specification, and the technical spirit disclosed in the specification is not limited by the accompanying drawings, and all modifications included in the spirit and technical scope of the present invention , It should be understood to include equivalents or substitutes.

Terms including ordinal numbers, such as first and second, may be used to describe various elements, but the elements are not limited by the terms. The terms are used only for the purpose of distinguishing one component from other components.

When an element is said to be "connected" or "connected" to another component, it is understood that other components may be directly connected to or connected to the other component, but there may be other components in between. It should be. On the other hand, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle.

Singular expressions include plural expressions unless the context clearly indicates otherwise.

In the present application, terms such as "comprises" or "have" are intended to designate the presence of features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, but one or more other features. It is to be understood that the presence or addition of elements or numbers, steps, actions, components, parts, or combinations thereof does not preclude in advance.

1 is a cross-sectional side view of a washing machine according to an exemplary embodiment of the present invention, and FIG. 2 is a block diagram illustrating a control relationship between main components of the washing machine of FIG. 1.

Referring to Figure 1, the washing machine according to an embodiment of the present invention, the casing (1) forming the appearance, and the reservoir (3) is disposed in the casing (1) and stored in the washing water (or tub (Tub)), It is installed to be rotatable in the water storage tank 3 and includes a washing tank 4 into which laundry is input, and a motor 9 for rotating the washing tank 4.

The washing tank 4 is provided with a front cover 41 having an opening for entering and exiting laundry, a cylindrical drum 42 disposed substantially horizontally and coupled with the front cover 41, and a rear end of the drum 42. It includes a rear cover 43 to be coupled. The rotating shaft of the motor 9 may pass through the rear wall of the water storage tank 3 and be connected to the rear cover 43. A plurality of through holes may be formed in the drum 42 so that water can be exchanged between the washing tank 4 and the storage tank 3.

A lifter 20 may be provided on the inner circumferential surface of the drum 42. The lifter 20 has a shape protruding from the inner circumferential surface of the drum 42 and extends long in the longitudinal direction (front and rear direction) of the drum 42, and a plurality of lifters may be spaced apart in the circumferential direction. When the washing tank 4 is rotated, the fabric may be pumped up by the lifter 20.

Although not necessarily limited thereto, the height of the lifter 20 protruding from the drum 42 may be preferably 30 mm (or 6.0% of the drum diameter) or less, more preferably 10 to 20 mm. Particularly, when the height of the lifter 20 is 20 mm or less, even if the washing tank 4 is continuously rotated in one direction at approximately 80 rpm, the fabric may flow without sticking to the washing tank 4. That is, when the washing tank 4 is rotated more than one revolution in one direction, the fabric located at the bottom of the washing tank 4 rises to a predetermined height by the rotation of the washing tank 4 and then is separated from the washing tank 4 and dropped. Can be.

The washing tank 4 is rotated about a horizontal axis. Here, "horizontal" does not mean geometric horizontal in a strict sense, and even when inclined at a predetermined angle with respect to horizontal as shown in FIG. 1, it is a case closer to horizontal than vertical, and the washing tub 4 It is assumed that it is rotated about a horizontal axis.

A laundry inlet is formed on the front surface of the casing 1, and a door 2 for opening and closing the laundry inlet is rotatably provided in the casing 1. Inside the casing 1, a water supply valve 5, a water supply pipe 6, and a water supply hose 8 may be installed. When the water supply valve 5 is opened to supply water, the washing water that has passed through the water supply pipe 6 is mixed with the detergent in the dispenser 7 and then can be supplied to the water storage tank 3 through the water supply hose 8.

The input port of the pump 11 is connected to the water storage tank 3 by the discharge hose 10, and the discharge port of the pump 11 is connected to the drain pipe 12. The water discharged from the water storage tank 3 through the discharge hose 10 is pumped by the pump 11 and flows along the drain pipe 12, and then discharged to the outside of the washing machine.

Referring to Figure 2, the washing machine according to an embodiment of the present invention, the control unit 60 for controlling the overall operation of the washing machine, the control unit 60, the motor drive unit 71, the output unit 72, the communication unit It may include a 73, a speed sensor 74, a current sensor 75, a vibration detector 76, a UB detector 77 and a memory 78.

The control unit 60 may control a series of washing processes such as washing, rinsing, dehydration and drying. The control unit 60 may perform washing, rinsing, dehydration, and drying strokes according to a preset algorithm, and the control unit 60 may control the motor driving unit 71 according to the algorithm.

The motor driving unit 71 may control driving of the motor 9 in response to a control signal applied from the control unit 60. The control signal may be a signal that controls the target speed, acceleration gradient (or acceleration), and driving time of the motor 9.

The motor driving unit 71 is for driving the motor 9 and may include an inverter (not shown) and an inverter control unit (not shown). In addition, the motor driving unit 71 may be a concept that further includes a converter or the like that supplies DC power input to the inverter.

For example, when the inverter control unit (not shown) outputs a pulse width modulation (PWM) switching control signal to the inverter (not shown), the inverter (not shown) performs a high-speed switching operation to supply AC power with a predetermined frequency. It can be supplied to the motor 9.

In this specification, explaining that the control unit 60 controls the motor 9 in a specific manner means that the control unit 60 applies a control signal to the motor driving unit 71 so that the motor 9 is controlled in a specific manner. , It may mean that the motor driver 710 controls the motor 9 in the specific manner based on the control signal. Here, the specific method may include various embodiments described herein.

The speed sensor 74 detects the rotational speed of the washing tank 4. The speed sensor 74 may sense the rotational speed of the rotor of the motor 9. When a planetary gear train that rotates the washing tank 4 by converting the rotation ratio of the motor 9 is provided, the rotational speed of the washing tank 4 is the rotational speed of the rotor sensed by the speed sensor 74. It may be a value converted by considering the reduction or increase ratio of the planetary gear train.

The control unit 60 may control the motor driving unit 71 so that the motor 9 follows the preset target speed by using the rotation speed of the washing tank transmitted from the speed sensing unit 74 as feedback. In other words, the control unit 60 may control the motor 9 so that the rotation speed of the washing tank reaches the target speed.

The current sensing unit 75 may sense the current applied to the motor 9 (or the output current flowing through the motor 9) and transmit it to the control unit 60. The control unit 60 may detect the amount and quality of the foam using the received current.

At this time, the current values include values obtained in the process in which the washing tub 4 is accelerated toward the target speed (or the motor 9 is accelerated toward the preset target speed).

When the rotation of the motor 9 is controlled by vector control based on torque current and magnetic flux current, the current may be a torque axis (q-axis) component of the current flowing in the motor circuit, that is, torque current (Iq). have.

The vibration detection unit 76 serves to detect vibration generated in the water storage tank 3 (or washing machine) by the rotation of the washing tank 4 containing the cloth.

The washing machine according to an embodiment of the present invention may include a vibration sensor (or vibration measurement sensor). The vibration sensor may be provided at one point of the washing machine, for example, may be provided at one point of the water storage tank 3. For example, the vibration sensor may be included in the vibration detection unit 76.

The vibration detection unit 76 may receive a vibration value (or vibration signal) measured by the vibration sensor and transmit it to the control unit 60. In addition, the vibration detection unit 76 may calculate a vibration value (or vibration magnitude) of the water storage tank 3 (or washing machine) by using a vibration signal measured by a vibration sensor.

Meanwhile, the present invention may further include a UB sensing unit 77. The UB sensing unit 77 may detect an eccentric amount (a shaking amount) of the washing tank 4, that is, an unbalance (UB) of the washing tank 4. The UB detecting unit 77 may calculate a UB value that numerically represents the shaking of the washing tank 4.

The description of the UB sensing unit 77 will be described later in more detail.

The speed detection unit 74, the current detection unit 75, the vibration detection unit 76, and the UB detection unit 77 provided in the washing machine according to an embodiment of the present invention may be referred to as a sensing unit, and the sensing It can be understood as a concept included in wealth.

In addition, in the sensing unit, the rotational speed value (or speed value) of the washing tub 4 measured by the speed sensing unit 74, the current value applied to the motor 9 measured by the current sensing unit 75, and vibration A plurality of types of data (signals, information) including the vibration value of the storage tank 3 measured by the sensing unit 76 and the shaking value (UB value) of the washing tub 4 measured by the UB sensing unit 77 are measured You can (calculate).

The plurality of types of data may mean data related to UB (unbalanced) of the washing tank 4, data for measuring the UB of the washing tank 4, data generated by rotation of the washing tank 4, or the like. The plurality of types of data may be used to control the washing tank 4 in the dehydration process.

For example, the plurality of types of data is input as an input value of an artificial neural network learned through machine learning, and outputs a UB pattern used to determine deceleration or maintenance of the washing tank 4 in a dehydration process as an output value. Can be used.

Meanwhile, in the drawings, the speed sensing unit 74, the current sensing unit 75, the vibration sensing unit 76, and the UB sensing unit 77 are provided separately from the control unit 60, but are not limited thereto.

At least one of the speed sensing unit 74, the current sensing unit 75, the vibration sensing unit 76, and the UB sensing unit 77 may be provided in the control unit 60. In this case, the function/operation/control method performed by the speed detection unit 74, the current detection unit 75, the vibration detection unit 76, and the UB detection unit 77 is performed by the control unit 60. I can.

When the vibration detection unit 76 is included in the control unit 60 or is performed by the control unit 60, the vibration sensor is not included in the vibration detection unit 76, but separately provided at one point of the washing machine. Can be understood.

The output unit 72 may output various information related to the washing machine. For example, the output unit 72 outputs an operating state of the washing machine. The output unit 72 may be an image output device such as an LCD or LED that outputs a visual display, or a sound output device such as a speaker buzzer that outputs sound. Under the control of the control unit 60, the output unit 72 may output information about the amount of cloth or the quality.

The memory 78 includes a programmed artificial neural network, current patterns for each gun and/or for each gun, and a database (DB), a machine learning algorithm, and a current sensing unit constructed through machine learning based learning based on the current pattern ( The current value sensed by 75), the average value of the current values, the value processed by the parsing rule, and the data transmitted and received through the communication unit 73 may be stored.

In addition, the memory 78 determines various control data for overall control of the operation of the washing machine, washing setting data input by the user, washing time calculated according to the washing setting, washing course, etc., and whether or not an error occurs in the washing machine. Data for the purpose may be stored.

The communication unit 73 may communicate with a server connected to the network. The communication unit 73 may include one or more communication modules such as an Internet module and a mobile communication module. The communication unit 73 may receive various data such as learning data and algorithm updates from the server.

The controller 60 may update the memory 78 by processing various types of data received through the communication unit 73. For example, when the data input through the communication unit 73 is update data for a driving program pre-stored in the memory 78, the control unit 60 may update the memory 78 using the update data. . In addition, when the input data is a new driving program, the controller 60 may additionally store the new driving program in the memory 78.

Machine learning means that the computer learns through data and the computer takes care of the problem without the need for a person to directly instruct logic.

Deep Learning is an artificial intelligence technology that teaches computers how to think, based on artificial neural networks (ANNs) for constructing artificial intelligence, and allows computers to learn like humans without humans teaching them. . The artificial neural network (ANN) may be implemented in software form or in a hardware form such as a chip.

For example, the washing machine processes the current values sensed by the current sensing unit 75 based on machine learning, so that the characteristics of the laundry (cloth) introduced into the washing tank 4 (hereinafter referred to as the foam characteristic). Can grasp.

These fabric properties can include fabric volume and quality.

The controller 60 may determine the quality of each foam amount based on machine learning. For example, the controller 60 may determine the amount of cloth, and again determine which of the pre-classified categories according to the quality. These foams include the quality of the fabric, the degree of softness (e.g., soft/hard fabrics), the ability of the fabric to hold water (i.e., moisture content), and the difference in volume between dry and wet fabrics. It can be defined based on several factors.

The controller 60 inputs the current current value sensed by the current sensing unit 75 until the point at which the target speed is reached by machine learning, input data of an artificial neural network ) To detect the amount.

In addition, the controller 60 may determine (predict, estimate, calculate) various information related to the unbalance of the washing tub 4 of the present invention using an artificial neural network (ANN) learned through machine learning.

For example, the control unit 60 inputs a plurality of types of data described above as input values of the artificial neural network (ANN) to determine whether the UB of the washing tank 4 will increase, decrease, or remain in the future. Information about a predicted UB pattern (UB trend) may be calculated as a result value. Thereafter, the control unit 60 may accelerate, maintain, or decelerate the washing tub 4 based on the calculated UB pattern (or type of UB pattern).

Hereinafter, the UB sensing unit 77 for measuring the UB of the washing tub 4 of the present invention will be described in more detail.

The UB detection unit 77 may measure the unbalance (UB) of the washing tank 4 generated when the washing tank 4 containing the cloth rotates. Here, the unbalance of the washing tub 4 may mean a shaking of the washing tub 4 or a shaking value (or shaking degree) of the washing tub 4.

The UB detection unit 77 may measure (calculate) a shaking value (or shaking degree) of the washing tub 4 (or drum). Here, the shaking value of the washing tank 4 may be named as a UB value, an UB amount, an unbalanced value, an unbalanced amount, or an eccentric amount.

In this specification, UB (UnBalance) may mean an eccentric amount of the washing tank 4, that is, unbalance of the washing tank 4 or shaking of the washing tank 4.

The UB value is a value for indicating the size (or degree) of the shaking of the washing tank 4, and the amount of rotational speed change of the washing tank 4 (or the motor 9) or the washing tank 4 (or the motor 9) ) Can be calculated (calculated) based on the amount of acceleration change.

For example, the UB detection unit 77 receives the rotational speed value of the washing tub 4 (or motor 9) measured by the speed detection unit 74, and calculates the amount of change in the received rotational speed value. Can be used to calculate the UB value. Here, the amount of change in the rotational speed means, for example, a difference in rotational speeds measured every predetermined time, or a difference in rotational speeds measured each time the washing tub 4 is rotated by a predetermined angle, or a maximum rotational speed. It may mean the difference in minimum rotation speed.

For example, the UB sensing unit 77 may measure the rotational speed of the washing tank 4 measured by the speed sensing unit 74 at a predetermined angle, and measure the acceleration through a difference in the measured rotational speed. Thereafter, the UB detector 77 may calculate the UB value by using a value corresponding to an acceleration difference obtained by subtracting the minimum acceleration from the maximum acceleration among the measured acceleration values.

For example, the UB value may mean a predetermined value proportional to the amount of change in the rotational speed or a predetermined value proportional to the difference in acceleration.

The UB value may be calculated based on not only the rotational speed of the washing tank, but also the difference in the current value applied to the motor or the difference in the vibration value of the water storage tank 3 measured by the vibration sensor.

The UB of the washing tank 4 is based on the state (or characteristics of the cloth) of the cloth inserted in the washing tank 4 (for example, the amount of cloth, the quality of the cloth, the degree of the packing of the cloth, the state in which the cloth is disposed, and the moisture content of the cloth) It can be decided or changed.

For example, in the case where the fabrics are arranged to be lumped together in the washing tub 4 or if the fabrics are lumped together, the balance becomes bad (that is, the unbalance becomes severe), and accordingly, the shaking of the washing tub due to the rotation of the washing tub is It increases, and the UB value also increases.

When the shaking of the washing tank becomes large (when the UB value of the washing tank is increased), a large current load is applied to the motor 9 for high-speed rotation of the washing tank 4 in the dehydration stroke, resulting in high energy consumption and noise. Cause problems.

Conversely, if the fabric is uniformly disposed within the washing tank 4, or if the fabric is small, the balance is improved, and accordingly, even if the washing tank is rotated at a high speed, the shaking of the washing tank becomes smaller and the UB value becomes smaller. .

The washing machine according to an embodiment of the present invention may perform a defoaming process in a dewatering process to reduce the energy consumption and reduce the noise by reducing the UB value.

The fabric dispersing process means a process in which the fabric inserted in the washing tank 4 is uniformly placed or unpacked. When the fabric is uniformly disposed, or the agglomerated fabric is released, the unbalance of the washing tank 4 becomes small.

The present invention can provide a washing machine and a control method of the washing machine that perform an optimized dehydration stroke to reduce the unbalance of the washing tank 4.

Hereinafter, with reference to the accompanying drawings, an optimized control method for performing a cloth dispersion process so as to reduce the unbalance of the washing tub in the dehydration cycle will be described in more detail.

3 is a view for explaining a conventional dehydration process, Figure 4 is a view for explaining a dehydration process according to an embodiment of the present invention.

The present invention can provide a control method for reducing the unbalance of the washing tub 4 so that the spin-drying time is shortened when performing the spin-drying process after the washing and rinsing cycles. In order to reduce the unbalance of the washing tub 4, a fabric dispersion process of dispersing the fabric may be performed.

First, referring to FIG. 3, in the conventional case, the control unit 60 includes a first section T1 for determining the amount of cloth and a second section T2 for accelerating the washing tank 4 at a first rotational speed for dispersing the cloth. ), the rotation of the washing tank 4 may be maintained at a first rotational speed V1 for dispersing the fabric.

The section (T3) in which the rotation of the washing tank (4) is maintained at the first rotation speed (V1) may be referred to as a fabric dispersion control section or a first rotation speed maintenance section (S1).

In the maintenance section S1 in which the washing tank 4 is rotated at the first rotational speed V1 in one direction, fabric dispersion may be performed by rising and falling the fabric to a predetermined height.

For example, the cloth accommodated in the washing tank 4 may be raised to a predetermined height by the lifter 20 provided in the washing tank 4 when the washing tank 4 is rotated. Thereafter, the gun is dropped by gravity.

That is, when the rotational speed of the washing tank 4 is the first rotational speed V1, the flow of the fabric is possible. Due to this, the rotation speed of the washing tank 4 is maintained at the first rotation speed V1, and the fabric can be dispersed through the rise and fall of the fabric (flow of the fabric).

For example, the first rotational speed V1 may be set at a speed between 60 and 65 revolutions per minute (rpm).

Conventionally, in the maintenance section T3 in which the rotation of the washing tank 4 is maintained (S1) at the first rotational speed V1, the control unit 60 of the washing tank 4 generated by the rising and falling of the fabric The shaking value (i.e., UB value) was measured.

The method of measuring the UB value will be replaced with the contents described above.

For example, when the bunching of the fabric is large, the UB value is largely measured, and when the bunching of the fabric is small (that is, when the fabric is well loosened), the UB value is measured small. Here, the UB value may mean one value (ie, instantaneous value) measured at any one moment.

In addition, conventionally, the rotation of the washing tank 4 is maintained (S1), accelerated (S2), or stopped (S3) based on the UB value at any moment measured in the holding section T3. Three controls were performed.

For example, the washing machine 4 rotates at a second rotational speed faster than the first rotational speed when the UB value of any one moment measured in the maintenance section T3 is smaller than a first preset reference value. It is possible to accelerate the washing tank 4 (S2).

At this time, a section for accelerating the rotation speed of the washing tank 4 from the first rotation speed to the second rotation speed may be referred to as a second rotation speed acceleration section or an acceleration section T4.

In the washing machine, when the UB value at any moment measured in the maintenance section T3 is a value between the first reference value and a second preset reference value that is greater than the first reference value, the washing tub 4 rotates first It can be maintained (S1) to rotate at a speed. In this case, the execution time of the maintenance section T3 may be extended.

The washing machine short-circuits the rotation of the washing tank 4 to stop the rotation of the washing tank 4 (S3) when the UB value at any one moment measured in the maintenance section T3 is greater than the preset second reference value. Can. In this case, the washing tank 4 may stop rotation and restart the dehydration stroke from the initial stage of the dehydration process (for example, the amount detection section T1).

The first reference value and the second reference value may be preset for each fabric amount.

That is, shorting the rotation of the washing tank 4 may include the meaning of stopping (stopping) the rotation of the washing tank 4 or initializing the dehydration process.

In addition, the washing machine measures the UB value at any one moment in the acceleration section T4 in which the rotation speed of the washing tub 4 is accelerated from the first rotation speed to the second rotation speed, and the measured UB value is preset. When the third reference value was exceeded, control was performed to short-circuit the rotation of the washing tub 4 (S4). The third reference value may be preset according to the amount of cloth or the rotational speed at which the UB value is measured.

On the other hand, when the washing tank 4 is rotated at the second rotation speed V2, the fabric may be attached to the washing tank 4 and not fall. That is, the second rotational speed may be a minimum speed at which the cloth is attached to the washing tank 4 and does not fall by centrifugal force. In one example, the second rotation speed may be 108 rpm.

In the acceleration section T4 that accelerates from the first rotation speed to the second rotation speed, a portion of the gun may rise to a predetermined height and then fall. However, as the rotational speed of the washing tank approaches the second rotational speed, the number of falling cloths decreases.

Thereafter, the washing machine measures the UB value in the second rotational speed maintenance section T5 where the second rotational speed is maintained, and if the measured UB value is equal to or less than a preset reference value associated with the second rotational speed, the acceleration section ( Through T6), the washing tank 4 may be rotated at the maximum rotational speed Vmax. The maintenance section T7 in which rotation is maintained at the maximum rotational speed Vmax from the second rotational speed maintenance section T5 to the acceleration section T6 may be referred to as a high-speed dewatering process. Thereafter, after the rotation of the washing tank is maintained at the maximum rotational speed for a predetermined time, the dehydration process is terminated (T8).

On the other hand, conventionally, since the washing tub 4 is accelerated to rotate at the second rotational speed or short-circuited in the second rotational speed acceleration period T4, proper fabric dispersion was not achieved in the acceleration period. . In the second rotational speed acceleration section T4, an operation in which the fabric is gradually attached to the washing tank 4 by acceleration of the washing tank 4 was performed. Accordingly, it is difficult to classify the acceleration section T4 as a section in which the variance of the cloth is made.

In addition, conventionally, the operation performed in the cloth dispersing process is an operation in which the rotational speed of the washing tub 4 is maintained at the first rotational speed in the holding section T3 (S1), and an operation of accelerating to the second rotational speed ( S2) and the operation of shorting the rotation of the washing tub (S3, S4) were able to perform only three operations.

That is, in the prior art, in the process of dispersing the fabric, a control operation for decelerating the rotational speed of the washing tank was not performed.

In addition, conventionally, by determining whether the rotation of the washing tub 4 is short-circuited by using only the UB value at a certain moment, a malfunction of shorting the rotation of the washing tub is caused even in a situation where it is not necessary to short-circuit by the UB value measured as an error. There was a problem that occurred.

On the other hand, referring to Figure 4, the control method of the washing machine according to an embodiment of the present invention, the second to accelerate the rotational speed of the washing tank 4 from the first rotational speed (V1) to the second rotational speed (V2) It is also possible to provide a control method capable of performing dispersion in the rotational speed acceleration section T4.

Specifically, the control unit 60, as well as the operation of accelerating the washing tank 4 (S5, S8) so that the distribution of the cloth is performed in the second rotation speed acceleration section (T4), the rotation speed of the washing tank (4) Maintenance (S7), or may perform an operation of decelerating (S6) the rotational speed of the washing tank (4). That is, compared to the conventional, the control unit 60 of the present invention, in the second rotational speed acceleration section (T4), it is possible to further perform the maintenance control and deceleration control as well as acceleration control.

In addition, in the present invention, the controller 60 short-circuits (S9) the rotation of the washing tub when the measured UB value while accelerating the washing tub in the second rotational speed acceleration section T4 exceeds a preset reference value. Short circuit control can also be performed.

Accordingly, the present invention can be defined as a gun dispersion control section that performs gun dispersion not only in the first rotation speed maintaining section T3 but also in the second rotation speed acceleration section T4.

In addition, the present invention, by performing the cloth dispersion in the second rotational speed acceleration section (T4), it is possible to reduce the number of times the rotation of the washing tub 4 is short-circuited, thereby significantly reducing the spin-drying stroke time, and The energy consumed by the rotational short circuit can also be reduced.

In addition, the control unit 60 of the present invention does not depend on one UB value measured at any one moment, measures a plurality of types of data every predetermined time, and measures the plurality of types of measured data through machine learning. Based on the UB pattern input and output to the artificial neural network, the washing tank 4 may be rotated in a preset manner.

Through this, the present invention, when accelerating or shorting the washing tub 4 depending on one type of UB value measured at any one moment, the washing tub 4 malfunctions when the measured UB value corresponds to an error value. It is prevented from doing so, and accordingly, the dehydration stroke time can be significantly reduced.

Hereinafter, a control method of a washing machine according to an embodiment of the present invention described above will be described in more detail with reference to the accompanying drawings.

5 is a flowchart illustrating a typical control method of the present invention, and FIGS. 6, 7 and 8 are conceptual diagrams for explaining the control method described in FIG. 5.

First, the washing machine according to an embodiment of the present invention includes a washing tub 4 that accommodates a cloth (laundry) and is rotatably provided, a motor 9 that rotates the washing tub, and the motor so that the washing tub 4 is rotated. It may include a control unit 60 for controlling (9).

Referring to FIG. 5, when the dehydration process starts, the control unit 60 performs a step of rotating the washing tank 4 at a first speed (first rotational speed) V1 after detecting the amount of cloth. (S10).

Specifically, the control unit 60, so that the cloth accommodated in the washing tub 4 in the dehydration stroke is uniformly arranged, and the cloth is loosened (that is, the cloth is dispersed), and the washing tub 4 is set at a first rotational speed (V1) Can be rotated with

At this time, in the maintenance section in which the washing tub 4 is kept rotating at the first rotational speed V1, the cloth accommodated in the washing tub 4 rises to a predetermined height by the rotation of the washing tub 4 and then falls. Thus, fabric dispersion can be performed.

The control unit 60 may measure the UB value while the washing tank 4 is rotated at the first rotation speed V1 (S20). Specifically, the control unit 60, when the flow of falling after the fabric rises to a predetermined height by the rotation of the washing tank 4, the shaking value of the washing tank 4 generated by the flow (that is, UB value) Can be measured.

The measurement (calculation) of the UB value will be replaced with the contents described above.

The controller 60 may determine whether or not the measured UB value is greater than or equal to a preset reference value (S30). Here, when the measured UB value is greater than a preset reference value, the control unit 60 may short circuit the rotation of the washing tank 4 (or the rotation of the motor 9) (S40).

The preset reference value may mean an UB value allowable value (or an UB allowable value) for passing from the first rotational speed to the next dehydration process. The preset reference value is a reference value set for the first rotational speed, and may vary depending on the amount of cloth or the quality.

As described above, when the rotation of the washing tub 4 is short-circuited, the rotation of the washing tub 4 is stopped, and the control unit 60 may restart the spinning cycle from the beginning. That is, shorting the rotation of the washing tank 4 may mean that the dehydration process is initialized to start again from the beginning.

On the other hand, if the measured UB value is less than the preset reference value (if less than), the control unit 60, the washing tank 4, the first speed (first rotational speed) (V1) faster than the second speed (zero) Acceleration to the washing tank 4 may be started to rotate at 2 rotation speeds (V2) (S50).

When the washing tank 4 is rotated at the second rotation speed V2, the fabric may be attached to the washing tank 4 and not fall. That is, the second rotational speed may be a minimum speed at which the cloth is attached to the washing tank 4 and does not fall by centrifugal force. For example, the second rotation speed may be 108 rpm.

In the second acceleration section T4 that accelerates from the first rotational speed (eg, 60 rpm) to the second rotational speed (eg, 108 rpm), a portion of the gun may rise to a predetermined height and then fall. However, as the rotational speed of the washing tank approaches the second rotational speed, the number of falling cloths decreases.

When the UB value measured at the first rotational speed V1 is smaller than the preset reference value, the control unit 60 enters the acceleration section T4 for accelerating the washing tub 4 to the second rotational speed V2. Can. The acceleration section T4 may be referred to as a second rotational speed acceleration section T4.

The maintenance section T3 in which the washing tank 4 maintains rotation at a first rotational speed V1 and the acceleration in which the washing tank 4 accelerates from the first rotational speed V1 to the second rotational speed V2. In the section, dispersion of the fabric may be performed by falling after the fabric rises to a predetermined height. That is, due to this, the unbalance of the washing tank 4 can be eliminated to some extent.

That is, until the rotational speed of the washing tub 4 reaches the second rotational speed V2, the cloth dispersion is performed, and the rotational speed of the cleaning tank 4 is equal to the second rotational speed V2. When reached, the fabric is attached to the washing tub 4 and rotates, and the fabric dispersion may not be performed.

The present invention performs various controls so that the distribution of the cloth is performed even in the acceleration section T4 accelerated to the second rotational speed V2 before the rotational speed of the washing tank 4 reaches the second rotational speed V2. can do.

That is, the control unit 60 of the present invention, in the second rotational speed acceleration section T4 (that is, while the washing tank accelerates from the first rotational speed to the second rotational speed), so that the dispersion of the cloth is performed, In addition to acceleration or short circuit, it is possible to maintain or decelerate the rotation speed of the washing tank.

As described above, in order to perform acceleration, short-circuit control, or maintenance or deceleration control of the washing tank, the control unit 60 may have the washing tank 4 at a first rotational speed (first speed) V1 than the first rotational speed. While accelerating at a fast second rotational speed V2, it is possible to measure (calculate) a plurality of preset data types (S60).

The preset plurality of types of data may be data related to the rotation of the washing tank. For example, the plurality of preset types of data may be measured (calculated) through the speed sensing unit 74, the current sensing unit 75, the vibration sensing unit 76, and the UB sensing unit 77 described above. have.

The preset plurality of types of data include the rotational speed value (or speed value) of the washing tank 4 measured by the speed sensor 74 and the current value applied to the motor 9 measured by the current sensor 75. , The vibration value of the water storage tank 3 measured by the vibration detection unit 76 and the shaking value (UB value) of the washing tank 4 measured by the UB detection unit 77 may be included.

The plurality of types of data may mean data related to UB (unbalanced) of the washing tank 4, data for measuring the UB of the washing tank 4, data generated by rotation of the washing tank 4, or the like. The plurality of types of data may be used to control the washing tank 4 in the dehydration process.

For example, the plurality of types of data is input as an input value of an artificial neural network learned through machine learning, and outputs a UB pattern used to determine deceleration or maintenance of the washing tank 4 in a dehydration process as an output value. Can be used.

At this time, the control unit 60 of the present invention may not only measure one type of data (UB value) measured at any one moment, but may use the average value for a predetermined time as the plurality of types of data.

In addition, the control unit 60 may calculate the plurality of types of data every predetermined time in an acceleration section in which the washing tank 4 accelerates from the first rotational speed V2 to the second rotational speed.

For example, referring to FIG. 6, the control unit 60 may calculate the average value of the UB values for a predetermined time d1 as one of a plurality of types of data. Here, the predetermined time d1 means a predetermined time interval, not a moment, and may be set to about 1 second, for example.

The control unit 60 may calculate the average value of the UB values by averaging the UB values measured during the predetermined time d1, and determine the average value of the calculated UB values as one of a plurality of types of data.

Although not shown, as described in FIG. 6, the control unit 60 includes an average value of the rotational speed value of the washing tub measured for a predetermined time d1, and a current value applied to the motor 9 measured for a predetermined time d1. The average value of and the average value of the vibration value measured by the vibration sensor for a predetermined time d1 may be determined as at least one of the plurality of types of data.

That is, the plurality of types of data include the average value of the UB value during the predetermined time d1, the average value of the rotation speed of the washing tub during the predetermined time d1, and the current value applied to the motor during the predetermined time d1. It may include at least one of an average value and an average value of vibration values measured by the vibration sensor for a predetermined time d1.

Thereafter, the controller 60 may input the plurality of types of data as an input value of a pre-trained artificial neural network, and calculate a predicted UB pattern as a result (S70).

Here, the control unit 60 inputs a plurality of types of data described above as input values of the artificial neural network (ANN) to predict whether the UB of the washing tub 4 will increase, decrease, or will be maintained in the future. Information on the UB pattern (UB trend) can be calculated as a result value.

Here, the UB pattern may mean information indicating a UB trend indicating whether the UB (or UB value) of the washing tank 4 will be increased, maintained, or decreased in the future.

The UB pattern expected in the future may include a UB increase pattern indicating a pattern in which UB increases, a UB maintenance pattern indicating a pattern in which UB is maintained, and a UB decrease pattern indicating a pattern in which the UB decreases.

Thereafter, the controller 60 may accelerate, maintain, or decelerate the rotational speed of the washing tub 4 based on the calculated UB pattern (or the type of UB pattern) (S80 to S110). That is, the control unit 60 may control the motor 9 so that the washing tub 4 is rotated in a preset manner based on the calculated type of the UB pattern.

The washing tank 4 is rotated in a predetermined manner may include accelerating the rotational speed of the washing tank 4, maintaining the rotational speed of the washing tank, and decelerating the rotational speed of the washing tank. In addition, the rotation of the washing tank 4 in a predetermined manner may include shorting the rotation of the washing tank 4.

The UB maintenance pattern may mean trend information indicating a pattern in which the UB is maintained even if the rotation speed of the washing tank 4 is increased. If the expected UB pattern is a UB maintenance pattern, the controller 60 may predict (determine, judge) that the UB will be maintained even if the rotation speed of the washing tank 4 is increased (S80). In this case, the control unit 60 maintains the rotation speed of the washing tank 4 at the rotation speed at the time when the UB pattern is calculated (for example, any one rotation speed smaller than the second rotation speed V2). , It can be made to disperse the fabric (S90).

The UB increase pattern may mean trend information indicating a pattern in which the UB increases as the rotation speed of the washing tank 4 increases. For example, if the rotational speed of the washing tank 4 is increased while the fabric is aggregated at the current rotational speed, UB may increase. That is, if the UB pattern expected in the future is the UB increase pattern, the control unit 60 predicts (determines) that the UB increases as the rotational speed of the washing tub 4 increases, and decreases the rotational speed of the washing tub 4 Can be made (S80, S100). Through this, the controller 60 of the present invention decelerates the rotational speed of the washing tank 4 so as to be slower than the rotational speed at the time the UB pattern is measured, and distributes the cloth in the second rotational speed acceleration section T4. Certainly, it is possible to perform control to reduce UB.

The UB reduction pattern may mean trend information indicating a pattern in which the UB decreases as the rotational speed of the washing tub 4 increases. For example, if dehydration proceeds as the rotational speed of the washing tank 4 increases, a case in which the UB decreases may occur. That is, in the case of the predicted UB reduction pattern in the future, the controller 60 may accelerate the washing tub 4 so that the rotational speed of the washing tub 4 reaches the second rotational speed V2 (S80, S110).

Meanwhile, in the present invention, an artificial neural network (ANN) for calculating the expected UB pattern as a result value may be included. Information about the artificial neural network (ANN) may be pre-stored in the memory 78 or the control unit 60.

7 is a schematic diagram showing an example of an artificial neural network.

Deep learning technology, which is a kind of machine learning, may mean learning to descend to a deep level in multiple stages based on data.

Deep learning may represent a set of machine learning algorithms that extract core data from a plurality of data while sequentially passing through hidden layers.

The deep learning structure may include an artificial neural network (ANN), for example, the deep learning structure is composed of a deep neural network (DNN) such as a convolutional neural network (CNN), a recurrent neural network (RNN), or a deep belief network (DBN). Can be.

Referring to FIG. 7, an artificial neural network (ANN) may include an input layer, a hidden layer, and an output layer. Having multiple hidden layers is called a deep neural network (DNN). Each layer includes a plurality of nodes, and each layer is associated with the next layer. Nodes can be connected to each other with a weight.

An output from an arbitrary node belonging to the first hidden layer 1 becomes an input to at least one node belonging to the second hidden layer 2. At this time, the input of each node may be a value in which a weight is applied to the output of the node of the previous layer. Weight may refer to the connection strength between nodes. The deep learning process can also be seen as a process of finding an appropriate weight.

An artificial neural network (ANN) applied to a washing machine according to an embodiment of the present invention uses input data as a plurality of types of data (speed average, current average, vibration average, UB average), and UB measured by experiments. By using the pattern as result data, it may mean a supervised learning deep neural network (DNN).

The supervised learning may mean a method of machine learning for inferring a function from training data.

The artificial neural network (ANN) of the present invention experimentally measures the type of UB pattern (UB trend) (UB increase pattern, UB maintenance pattern, UB decrease pattern) for each of a plurality of types of data, and each plurality of types of data are input data. , By inputting the UB pattern measured for each of the plurality of types of data as a result value, the hidden layer may be a learned deep neural network. Here, training the hidden layer may mean adjusting (updating) the weight of a connection line between nodes included in the hidden layer.

Using such an artificial neural network (ANN), the control unit 60 of the present invention calculates a plurality of types of data at a certain point in time, and uses the plurality of types of data as input values of the artificial neural network, (UB increase pattern, UB maintenance pattern, UB decrease pattern) can be calculated (predicted, determined, estimated).

The controller 60 may perform learning by using a plurality of types of data corresponding to a rotational speed average value, a current average value, a vibration average value, and an UB average value as training data. That is, each time the control unit 60 recognizes or determines the expected UB pattern in the future, the result of the determination and a plurality of types of data input at the time are added to the database to deep network such as weight or bias ( DNN) structure can be updated. In addition, the controller 60 may update a deep neural network (DNN) structure such as a weight by performing a supervised learning process with the obtained training data after a predetermined number of training data is secured.

In addition, as shown in Figure 6, the control unit 60, in the acceleration section in which the washing tub 4 accelerates from the first rotation speed V1 to the second rotation speed V2, a predetermined time T' Each of the plurality of types of data can be measured (calculated).

The controller 60 may measure (calculate) a plurality of types of data every predetermined time T', and determine a control method of the washing tub 4 using the plurality of types of data.

At this time, the controller 60 measures a plurality of types of data for each of the predetermined time T', and based on the type of the UB pattern calculated through the artificial neural network using the measured plurality of types of data, the schedule It is possible to determine whether to accelerate, decelerate, or maintain the rotational speed of the washing tank 4 every time T'.

As described above, the calculated UB pattern (that is, the expected UB pattern in the future), the UB increase pattern expected to increase the UB value, the UB maintenance pattern expected to maintain the UB value and the UB value will decrease It may include the expected UB reduction pattern.

The control unit 60 calculates a plurality of types of data (that is, data corresponding to an average value during a predetermined time d1) for each predetermined time T', and artificially trained the calculated plurality of types of data. By inputting it as an input value to the neural network (ANN), the expected UB pattern in the future can be calculated as a result value.

When the calculated UB pattern is an UB increase pattern in which the UB value is expected to increase, the control unit 60 may reduce the rotational speed of the washing tub 4 (S80, S100). For example, the control unit 60 increases the UB value when the UB pattern calculated by inputting the plurality of types of data into the artificial neural network accelerates the washing tank 4 to rotate at the second rotational speed V2. In the case of the UB increase pattern that appears, the rotation speed of the washing tank 4 may be reduced (S100).

The control unit 60 may increase (acceleration) the rotation speed of the washing tank 4 when the calculated UB pattern is a UB reduction pattern that is expected to decrease the UB value (S80, S110). For example, the control unit 60 reduces the UB value when the UB pattern calculated by inputting the plurality of types of data into the artificial neural network accelerates the washing tank 4 to rotate at the second rotational speed V2. In the case of the UB reduction pattern that appears to be, the rotation speed of the washing tank 4 may be increased (accelerated) (S110).

The controller 60 may maintain the rotation speed of the washing tank 4 when the calculated UB pattern is a UB holding pattern expected to maintain the UB value. For example, the control unit 60 maintains the UB value when the UB pattern calculated by inputting the plurality of types of data into the artificial neural network accelerates to rotate the washing tub 4 at a second rotational speed V2. In the case of the UB maintenance pattern that appears to be the world, it is possible to maintain the rotation at the rotational speed of the washing tub 4 at the time when plural types of data are measured (S90).

Thereafter, the control unit 60 of the present invention may determine whether the rotation speed of the washing tank 4 has reached the second rotation speed V2 (S120).

When the rotational speed of the washing tank 4 does not reach the second rotational speed V2, the control unit 60 may return to step S60 every predetermined time (T′).

That is, the control unit 60 calculates (measures) a plurality of types of data for a predetermined time at each predetermined time T', inputs this as an input value of an artificial neural network to calculate a UB pattern, and calculates the calculated UB pattern. Based on, the rotation of the washing tub 4 can be controlled in a preset manner.

In this way, a series of processes (eg, S50 to S120) performed in the second rotational speed acceleration section T4 may be referred to as an intelligent four dispersion process.

When the rotation speed of the washing tank 4 reaches the second rotation speed V2, the control unit 60 may end the intelligent foam dispersion process and start a high-speed dehydration process (S130).

In the high-speed dehydration process, the UB value is measured at the second rotational speed V2, and if the measured UB value does not exceed the reference value, the washing tank 4 is rotated at the maximum rotational speed Vmax to proceed with dehydration. It may mean a process (see T5 to T8, FIGS. 3 and 4).

Here, the reference value may be an allowable UB value to enter the next dehydration process at the second rotational speed V2, and may vary depending on the amount of cloth or the quality.

On the other hand, when the UB value measured in the acceleration section T4 in which the washing tank 4 accelerates from the first rotational speed V1 to the second rotational speed V2 exceeds the reference value, the control unit 60 performs the washing tank ( The rotation of 4) can be shorted.

That is, the control unit 60, based on a plurality of types of data in the acceleration section (T4), in addition to the operation of accelerating, decelerating or maintaining the rotational speed of the washing tank (4), UB measured in the acceleration section (T4) When the value exceeds the reference value, control to short circuit the rotation of the washing tank 4 may be performed. Here, the measured UB value may mean an average UB value measured for a predetermined time (d1).

Here, the reference value may mean an allowable UB value set in the acceleration section T4, and may have different reference values for each rotational speed (or a predetermined rotational speed section) of the washing tank 4, or may vary depending on the amount or the quality of the foam. It can have a reference value.

On the other hand, the control unit 60, when the washing tank 4 does not reach the second rotational speed within a preset time from the start of the acceleration from the first rotational speed (V1) to the second rotational speed (V2), It is also possible to short circuit the rotation of the washing tank 4.

Specifically, the control unit 60 in the acceleration section (T4) for the washing tank 4 to accelerate from the first rotational speed (V1) to the second rotational speed (V2), the predetermined time (for example, 300 seconds) ), if the second rotation speed is not reached (that is, if the second rotation speed maintenance section T5 is not entered within the preset time), the rotation of the washing tank 4 is short-circuited and the dehydration process is started for the first time. You can start over.

When the time required for the acceleration section T4 in which the washing tank 4 accelerates from the first rotational speed V1 to the second rotational speed V2 exceeds the preset time, the control unit 60 may The rotation of (4) can be shorted.

For example, in the acceleration section T4, the controller 60 accelerates the rotational speed of the washing tub 4 based on the UB pattern calculated using a plurality of types of data measured every predetermined time as an input value, You can perform deceleration or holding control. At this time, when the rotational speed of the washing tank 4 does not reach the second rotational speed V2 within the preset time by the control, the control unit 60 starts the dehydration process from the beginning and distributes the cloth. You can do it again from scratch. Through this, the present invention has the effect of reducing noise at the highest rotational speed by allowing a more complete foam dispersion to be performed and then entering a high-speed dehydration process.

As another example, when the rotation speed of the washing tank 4 does not reach the second rotation speed V2 within the preset time by the control in the acceleration section T4, the control unit 60 may perform the operation. Based on the lapse of the set time, the rotation speed of the washing tank 4 can be accelerated so that the rotation speed of the washing tank 4 reaches the second rotation speed, rather than shorting the rotation of the washing tank 4. Through this, the present invention has an effect that the dehydration stroke time can be prevented from being continuously extended.

On the other hand, the control unit 60 of the present invention, even in the first rotational speed maintenance section (T3), the contents described in Figures 5 to 7 can be applied analogously/similarly.

For example, the control unit 60 may calculate (measure) a plurality of types of data every predetermined time T'in the first rotational speed maintenance section T3.

The plurality of types of data may mean an average value of data measured during a predetermined time d1, for example, an average value of the rotation speed of the washing tank, an average current value applied to the motor, an average vibration value of the water storage tank, and an average UB value of the washing tank. .

The controller 60 may input a plurality of types of data measured in the first rotational speed maintenance section T3 as an input value of a previously learned artificial neural network, and calculate a UB pattern expected in the future as a result value.

Thereafter, the controller 60 may enter the second rotational speed acceleration section T4 based on the calculation of the UB pattern. At this time, when the controller 60 enters the second rotational speed acceleration section T4, whether to accelerate the rotational speed of the washing tank 4 or to slow down the rotational speed of the washing tank 4, the washing tank 4 Whether to maintain the rotational speed of can be determined based on the calculated UB pattern.

That is, when the UB pattern calculated in the first rotational speed maintenance section T3 is the UB increase pattern, the control unit 60 decelerates the rotational speed of the washing tub 4 and the second rotational speed acceleration period T4 You can enter.

When the UB pattern calculated in the first rotation speed maintenance section T3 is a UB reduction pattern, the controller 60 accelerates the rotation speed of the washing tank 4 and enters the second rotation speed acceleration section T4. can do.

However, when the UB pattern calculated in the first rotation speed maintenance section T3 is the UB maintenance pattern, the control unit 60 may maintain the rotation speed of the washing tank 4 at the first rotation speed. In this case, the first rotation speed maintenance section T3 may be continuously maintained.

After a certain period of time T'has elapsed, the control unit 60 measures (calculates) the plurality of types of data again in the first rotational speed maintaining section T3, and inputs it to the previously learned artificial neural network. UB pattern can be recalculated. Thereafter, the control unit 60 may accelerate, decelerate, or maintain the rotational speed of the washing tank 4 based on the recalculated UB pattern.

On the other hand, if the UB value measured in the first rotational speed maintenance section T3 does not exceed a preset reference value, the control unit 60 continues to be the first if the calculated and recalculated UB pattern is still a UB maintenance pattern. In order to stop staying in the rotational speed maintaining section T3, acceleration may be started so that the washing tub 4 accelerates to the second rotational speed V2 based on the lapse of a predetermined time (ie, the second rotational speed). You can enter the acceleration section (T4)).

As described above, the control method performed in the intelligent distribution and distribution processes (S60 to S110) performed in the second rotational speed acceleration section T4 of the present invention may be applied analogously/similarly to the first rotational speed maintenance section T3. Can.

The intelligent focal dispersion process according to an embodiment of the present invention described above will be more clearly understood through FIG. 8.

Referring to Figure 8, the control unit 60 of the present invention, when entering the dehydration stroke, the first rotational speed maintenance section to maintain the rotation of the washing tank 4 at the first rotational speed (V1), so that the distribution of the cloth is made You can enter (T3).

In the first rotational speed maintenance section T3, fabric dispersion may be performed by dropping the fabric contained in the washing tank 4 to a predetermined height and then falling.

If the UB value measured in the first rotational speed maintenance section T3 does not exceed the reference value (if less), the controller 60 rotates the washing tank 4 at a second rotation faster than the first rotational speed V1. In order to rotate at the speed V2, the second rotation speed acceleration section T4 may be entered.

At this time, the control unit 60, in the acceleration section (T4) in which the washing tank (4) accelerates from the first rotational speed (V1) to the second rotational speed (V2), a plurality of types of data for a certain time (T') Can be measured.

In this case, the plurality of types of data may be average values of data measured for a predetermined time (d1, see FIG. 6), not instantaneous values measured at any one moment, and average values of rotation speed of the washing tank and applied to the motor It may include the current average value, the vibration average value of the water storage tank 3 and the UB average value of the washing tank 4.

The controller 60 may measure the plurality of types of data every predetermined time (T') and input the measured plurality of types of data into a pre-trained artificial neural network to calculate a predicted UB pattern in the future.

The UB pattern includes a UB increase pattern expected to increase the UB value when the rotation of the washing tub is accelerated, a UB maintenance pattern expected to maintain the UB value, and a UB decrease pattern expected to decrease the UB value. can do.

After entering the second rotational speed acceleration section T4, the control unit 60 measures a plurality of types of data preset at a first time point C1, and the measured plurality of types of data are applied to a previously learned artificial neural network. By input, it is possible to calculate the expected UB pattern in the future.

Here, when the calculated UB pattern is a UB reduction pattern, the control unit 60 may accelerate the rotation speed of the washing tank 4.

Thereafter, at a second time point C2 when a predetermined time T'has elapsed, the control unit 60 may calculate the plurality of types of data again. The control unit 60 may input a plurality of types of data calculated at the second time point C2 back into the pre-trained artificial neural network to calculate an expected UB pattern in the future.

Here, when the calculated UB pattern is a UB increase pattern, the control unit 60 may decelerate the rotation speed of the washing tank 4.

Thereafter, at a third and fourth time points C3 and C4 after a predetermined time T', the controller 60 may recalculate the plurality of types of data. The control unit 60, if all of the UB pattern calculated in the artificial neural network using a plurality of types of data calculated at the third and fourth time points (C3, C4) is a UB maintenance pattern, the second time point (and the It is possible to maintain the rotational speed of the washing tank 4 at the third time point).

Thereafter, a plurality of types of data are recalculated at a fifth time point C5 after a predetermined time T'has elapsed from the fourth time point C4, and the calculated plurality of types of data are input to a pre-trained artificial neural network. When the calculated UB pattern is a UB reduction pattern, the control unit 60 may increase (acceleration) the rotation speed of the washing tank 4.

In addition, the control unit 60, the UB value measured in the second rotational speed acceleration section (T4) does not exceed a preset reference value, but the rotation of the washing tub 4 in the second rotational speed acceleration section (T4). The time during which the speed is maintained at a predetermined rotational speed elapses more than a preset first time (e.g., 2T'), or the required time of the second rotational speed acceleration section T4 is a preset time (e.g., 4T). ') Based on the lapse of the above, the washing tub 4 may be accelerated to rotate at the second rotational speed V2.

The contents described above can be applied analogously/similarly to the control method of the washing machine. The control method of the washing machine may be performed by, for example, the control unit 60.

According to an embodiment of the present invention, one or more of the following effects are provided.

First, according to the present invention, the cloth is distributed in the acceleration section that accelerates to the second rotational speed faster than the first rotational speed from the first rotational speed, as well as the maintenance section where the washing tank maintains rotation at the first rotational speed Optimized fabric dispersion can be performed by widening the section where dispersion is performed, and this has the effect of reducing the dehydration stroke time.

Second, the present invention accelerates the rotational speed of the washing tank based on the UB pattern predicted in the future by using the artificial neural network learned through machine learning in an acceleration section that accelerates from the first rotational speed to the second rotational speed. In addition to maintaining and decelerating the control, the dehydration stroke time can be significantly reduced by reducing the number of times the dehydration stroke is short-circuited.

Third, the present invention determines a method of controlling the rotational speed of the washing tub by using a plurality of types of data measured for a predetermined time, not one type of data measured at a certain moment, so that one measured data is In the case of an error value, there is an effect that it is possible to prevent the dehydration stroke time from being delayed by shorting the dehydration stroke.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

The present invention described above can be implemented as a computer-readable code on a medium on which a program is recorded. The computer-readable medium includes all kinds of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SDD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. There is this. In addition, the computer may include a processor or a control unit. Accordingly, the above detailed description should not be construed as limiting in all respects, but should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

Claims (17)

A laundry tub that accommodates the fabric and is rotatably provided;
A motor that rotates the washing tub; And
It includes a control unit for controlling the motor to rotate the washing tub,
The control unit,
While the washing tub is accelerating from a first rotation speed to a second rotation speed faster than the first rotation speed, a plurality of preset types of data are measured,
By inputting the plurality of types of data as input values of the previously learned artificial neural network, the UB pattern expected in the future is calculated as a result value,
And controlling the motor to rotate the washing tub in a predetermined manner based on the calculated type of UB pattern. The method of claim 1,
In the maintenance section in which the washing tub is maintained rotating at the first rotational speed and the acceleration section in which the washing tub is accelerated from the first rotational speed to the second rotational speed, the fabric is dispersed by falling after rising to a predetermined height. Washing machine, characterized in that this is carried out. According to claim 2,
Until the rotational speed of the washing tub reaches the second rotational speed, the cloth dispersion is performed,
When the rotational speed of the washing tub reaches the second rotational speed, the cloth is attached to the washing tub and rotates, and the cloth dispersion is not performed. The method of claim 1,
The plurality of types of data are the average value of the UB value for a predetermined time, the average value of the rotation speed value of the washing tub for a predetermined time, the average value of the current value applied to the motor for a predetermined time, and measured by a vibration sensor for a predetermined time. A washing machine comprising at least one of an average value of vibration values. The method of claim 1,
The control unit,
And measuring the plurality of types of data every predetermined time in an acceleration section in which the washing tub accelerates from the first rotation speed to the second rotation speed. The method of claim 5,
The control unit,
The plurality of types of data are measured at each predetermined time, and based on the type of UB pattern calculated through an artificial neural network using the measured plurality of types of data, the rotation speed of the washing tub is accelerated, decelerated, or Washing machine, characterized in that to determine whether to maintain. The method of claim 1,
The calculated UB pattern,
A washing machine comprising: an UB increase pattern in which an UB value is expected to increase, an UB maintenance pattern in which the UB value is expected to be maintained, and a UB decrease pattern in which the UB value is expected to decrease. The method of claim 7,
The control unit,
When the calculated UB pattern is a UB increase pattern in which the UB value is expected to increase, the washing machine is characterized in that the rotational speed of the washing tub is reduced. The method of claim 7,
The control unit,
When the calculated UB pattern is a UB reduction pattern in which the UB value is expected to decrease, the rotation speed of the washing tub is increased. The method of claim 7,
The control unit,
When the calculated UB pattern is an UB maintenance pattern in which the UB value is expected to be maintained, the washing machine maintains the rotational speed of the washing tub. The method of claim 1,
The control unit,
When the UB value measured in an acceleration section in which the washing tub accelerates from the first rotation speed to the second rotation speed exceeds a reference value, the rotation of the washing tub is short-circuited. The method of claim 1,
The control unit,
A washing machine, characterized in that, when the washing tub does not reach the second rotation speed within a preset time from a time when the washing tub starts to accelerate from the first rotation speed to the second rotation speed, the rotation of the washing tub is short-circuited. Measuring a plurality of preset types of data while the washing tub accelerates from the first rotation speed to a second rotation speed that is faster than the first rotation speed;
Inputting the plurality of types of data as input values of a previously learned artificial neural network, and calculating a UB pattern expected in the future as a result value; And
And controlling a motor so that the washing tub rotates in a preset manner based on the calculated type of UB pattern. The method of claim 13,
The calculated UB pattern,
A method of controlling a washing machine, comprising: an UB increase pattern in which the UB value is expected to increase, an UB maintenance pattern in which the UB value is expected to be maintained, and a UB decrease pattern in which the UB value is expected to decrease. The method of claim 14,
The controlling step,
When the calculated UB pattern is a UB increase pattern in which an UB value is expected to increase, the rotational speed of the washing tub is reduced. The method of claim 14,
The controlling step,
When the calculated UB pattern is a UB reduction pattern in which the UB value is expected to decrease, the rotation speed of the washing tub is increased. The method of claim 14,
The controlling step,
When the calculated UB pattern is an UB holding pattern in which the UB value is expected to be maintained, the control method of a washing machine, wherein the rotational speed of the washing tub is maintained.

Images