JPH05199947A - Toilet device - Google Patents

Abstract

PURPOSE:To execute comfortable heating by inputting a temperature of a lavatory seat, a physical quantity for exerting influence on the temperature of the lavatory seat and a surface temperature estimated from the physical quantity, to a control means, and controlling electric conduction to a heating element of the lavatory seat. CONSTITUTION:A temperature is detected 5 by a temperature detecting body 3 of a lavatory seat main body 1 and inputted to a control means 7. Also, a physical quantity for exerting influence on the temperature of the lavatory seat main body 1, for instance, the physical quantity of a time counting means 10, a seated state detecting means l2, a temperature setting means 6 and a room temperature detecting means 9, etc., is derived by a measuring means 8 and inputted to the control means 7. On the other hand, an output of a physical quantity measuring means 8 is inputted to a surface temperature estimating means 13, and an estimated value of a surface temperature obtained by modeling and learning a neural network, and inputted to the controller 7. The controller 7 calculates these input values, and controls turn-on/turn-off of electric conduction to a heating element of the lavatory seat 1. In such a manner, comfortable heating is executed.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a toilet device for controlling a heating element based on the surface temperature of a toilet seat body.

[0002]

2. Description of the Related Art Conventionally, this type of toilet device has been constructed as shown in FIG. The configuration will be described below.

As shown in the figure, the toilet seat body 1 has a heating element 2 and a temperature detecting element 3 arranged therein. The energization control means 4 controls energization to the heating element 2 and is composed of a relay or the like. The temperature detecting means 5 detects the temperature of the heating element 2 via the temperature detecting element 3. The temperature setting means 6 determines a set temperature. The control means 7 controls the energization control means 4 based on the outputs of the temperature detection means 5 and the temperature setting means 6.

[0004]

In such a conventional toilet device, the heating element 2 is detected by detecting the surface temperature of the toilet seat body 1.
However, there is a problem in that the actual surface temperature fluctuates considerably depending on the environment in which the toilet seat body 1 is used. For example, the actual surface temperature during operation differs depending on the difference in room temperature. This is shown in FIG. Further, as shown in FIG. 10, when the user opens the window and the outside air having a low temperature is taken into the room, the surface temperature drops sharply, but since the temperature detector 3 is inside the toilet seat body 1, the surface temperature is low. It takes time to detect a decrease in temperature. Furthermore, when the user is seated, the surface temperature of the toilet seat changes differently from that when the user is not seated due to heat transfer between the toilet seat body and the human body. In other words, the actual surface temperature differs considerably from the temperature set by the temperature setting means 6 depending on the environment in which the toilet seat body 1 is used (room temperature, seated state, etc.). This problem can be solved by providing a sensor for detecting the surface temperature of the toilet seat body 1 on the surface, but it was difficult to express it as a product.

The present invention solves the above-mentioned problems. By estimating the surface temperature of the toilet seat body in real time with a physical quantity that can be actually measured and detected, comfortable heating can be obtained regardless of the environment used. That is the first purpose. The second purpose is to easily estimate the surface temperature of the toilet seat body by a multidimensional information processing method.

[0006]

In order to achieve the first object, the present invention provides a toilet seat body having a heating element and a temperature detecting element, and the temperature of the heating element via the temperature detecting element. Temperature detecting means for detecting, energization controlling means for controlling energization to the heating element, physical quantity measuring means for measuring and setting a physical quantity affecting heat generation of the toilet seat body, the temperature detecting means, the physical quantity measuring means The first problem-solving means is composed of a surface temperature estimating means for estimating the surface temperature of the toilet seat body based on the output of the above, and a control means for controlling the energization controlling means based on the output of the surface temperature estimating means. ..

Further, in order to achieve the second object, the surface temperature estimating means of the first problem solving means is obtained by a method of modeling a neural network composed of a plurality of neural elements as a toilet seat. Having a neural network schematic means internally having a plurality of fixed coupling weight coefficients for estimating the surface temperature of the body, or of a hierarchical type constructed by combining a number of layers composed of a plurality of neural elements Having the neural network model means is the second means for solving the problem.

[0008]

According to the first aspect of the present invention, the surface temperature estimating means is provided by inputting the temperature information of the temperature detecting body from the temperature detecting means and the physical quantity measuring information from the physical quantity measuring means to the surface temperature estimating means. Estimates the surface temperature of the toilet seat body from moment to moment. Using the surface temperature information, the control means can control the heating element via the energization control means to obtain comfortable heating.

According to the second problem solving means, the neural network schematic means constituting the surface temperature estimating means is provided with the connection weight coefficient already learned under the environment in which it is used,
It is possible to estimate the surface temperature of the toilet seat body in an environment that changes moment by moment.

[0010]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to FIGS. The same components as those in the conventional example are designated by the same reference numerals and the description thereof will be omitted.

As shown in the figure, the physical quantity measuring means 8 measures and sets the physical quantity that affects the heat generation of the valve seat body 1. The room temperature detecting means 9 is composed of a thermistor and its peripheral circuit. The timekeeping means 10 counts the time since the power was turned on. The duty ratio detecting means 11 detects the duty ratio to the heating element 2. The seating detection means 12 detects whether or not the user is seated on the toilet seat, and is composed of a micro switch. The physical quantity measuring means 8 includes a temperature setting means 6, a room temperature detecting means 9, a time measuring means 10, a duty ratio detecting means 11, and a seating detecting means 12. The surface temperature estimating means 13 estimates the surface temperature of the toilet seat body 1 based on the outputs of the temperature detecting means 5, the temperature setting means 6, the room temperature detecting means 9, the time measuring means 10, the duty factor detecting means 11, and the seating detecting means 12. Yes, the control means 7 is the surface temperature estimation means 13
The energization control means 4 is controlled based on the output of. Toilet seat body 1
The heat generating element 2 and the temperature detecting element 3 are respectively arranged in the.

The means constituting the surface temperature estimating means 13 is
Since the resolving method used in the conventional control method cannot be applied, the method is constructed by a model of an optimal neural network as a multidimensional information processing method. Methods using a neural network as a model include a method of using a plurality of connection weight coefficients as a fixed table and a method of leaving a learning function so that it can be adapted to the environment and the user. The present embodiment is obtained by a method using a neural network as a model, and the surface temperature estimating means 13 has a neural network model means having therein a plurality of fixed coupling weight coefficients for estimating the surface temperature of the toilet seat body 1. Is provided.

The physical quantities that affect the heat generation on the surface of the toilet seat body 1 include the temperature of the heating element, room temperature, set temperature, the time elapsed after the power is turned on, the energization rate, and the sitting state.
In the toilet seat body 1, the heat of the heating element 2 is transferred in the horizontal direction, the front surface direction (upward), and the back surface direction (downward), but the heat of the heating element 2 is transferred depending on the surrounding environment (room temperature, etc.). One is different. Therefore, the surface temperature of the toilet seat body 1 varies greatly depending on the surrounding environment.

The coupling weight coefficient in the neural network for estimating the surface temperature of the toilet seat body 1 is determined by how the surface temperature of the toilet seat body 1 is controlled when the heating element 2 is controlled in various environments where the toilet device is used. It can be obtained by collecting data on whether or not it changes, and making the neural network schematic means learn the correlation between environmental data, control data, and surface temperature data. As a neural network schematic means to be used, reference 1 (DE Ramelhart et al., 2 authors, Shunichi Amari supervised "PDP model" 1989), reference 2 (Kaoru Nakano, 7 authors, "Basics of Neurocomputer") Published by Corona, P102, 1990), Japanese Patent Publication No. 63-5510
There is one disclosed in Japanese Patent No. 6 or the like. Hereinafter, the configuration and operation of a concrete neural network schematic means will be described by taking a multilayer perceptron using an error backpropagation method as the most well-known learning algorithm described in Document 1 as an example.

FIG. 3 is a conceptual diagram of a neural element which is a constituent unit of the neural network model means. In FIG. 3, 21 to 2
N is a pseudo synapse coupling converter simulating synaptic coupling of nerves, and 2a is pseudo synapse coupling converters 21 to 2N.
2b is a set nonlinear function, for example, a sigmoid function whose threshold is h, f (y, h) = 1 / (1 + exp (-y + h)) (Equation 1 ) Is a non-linear converter for non-linearly converting the output of the adder 2a. Although omitted because the drawing is complicated, an input line for receiving a correction signal from the correction means is connected to the pseudo synapse coupling converters 21 to 2N and the non-linear converter 2b. Further, the pseudo synapse coupling converters 21 to 2N serve as coupling weight coefficients of the neural network schematic unit. This neural element has two types of operation modes, a signal processing mode and a learning mode.

The operation of each mode of the neural element will be described below with reference to FIG. First, the operation of the signal processing mode will be described. Neural elements are N inputs X1 to X
It receives n and outputs one output. i-th input signal Xi
Is the i-th pseudo-synaptic coupling converter 2 shown by a square
i is converted to Wi · Xi. N signals W1 · X1 converted by the pseudo synapse coupling converters 21 to 2N
Wn · Xn enters the adder 2a, the addition result y is sent to the nonlinear converter 2b, and becomes the final output f (y, h). Next, the operation of the learning mode will be described. In the learning mode, the conversion parameters W1 to Wn and h of the pseudo synapse coupling converters 21 to 2N and the non-linear converter 2b are received by a correction signal representing the correction parameter correction amounts ΔW1 to ΔWn and Δh from the correction means, and Wi + ΔWi ; I = 1, 2, ..., N h + Δh (formula 2) is corrected.

FIG. 4 is a conceptual diagram of a signal converting means constituted by connecting four neural elements in parallel. In the following description, the number of neural elements that make up this signal conversion means is 4
It is not limited to individual items. In FIG. 4, 211-2
44 is a pseudo synapse coupling converter, and
Is an addition nonlinear converter in which the adder 2a and the nonlinear converter 2b described in FIG. 3 are combined. 4, the illustration is omitted because it is complicated as in FIG. 3, but the input line for receiving the correction signal from the correction means is the pseudo synapse coupling converter 2.
11 to 244 and the addition nonlinear converters 201 to 204. The pseudo synapse coupling converters 211 to 244 also serve as coupling weight coefficients. Regarding the operation of this signal conversion means, the operation of the neural element described in FIG. 3 is performed in parallel.

FIG. 5 is a block diagram showing the configuration of the signal processing means when the error back propagation method is adopted as the learning algorithm, and 31 is the above-mentioned signal conversion means. However,
Here, M neural elements for receiving N inputs are arranged in parallel. Reference numeral 32 is a correction means for calculating the correction amount of the signal conversion means 31 in the learning mode. Hereinafter, the operation when learning the signal processing means will be described with reference to FIG. The signal converting means 31 has N inputs S
Upon receiving _in (X), it outputs M outputs S _out (X).
The correction means 32 includes an input signal S _in (X) and an output signal S _out.
After receiving (X), the process waits until M error signals δ _j (X) are input from the error calculating means or the signal converting means in the subsequent stage. The error signal δ _j (X) is input and the correction amount is set to ΔW _ij = δ _j (X) · S _jout (X) · (1-S _jout (X)) · S _jin (X) (i = 1 to N, j = 1 to M) (Equation 3) is calculated, and the correction signal is sent to the signal conversion means 31. The signal conversion means 31 modifies the conversion parameters of the internal neural elements according to the learning mode described above.

FIG. 6 is a block diagram showing the structure of a multilayer perceptron using a neural network model.
X, 31Y, and 31Z are signal conversion means composed of K, L, and M neural elements, respectively, and are 32X, 32Y, and 3X.
2Z is a correction means, and 33 is an error calculation means. The operation of the multi-layer perceptron configured as described above will be described with reference to FIG. Signal processing means 3
In 4X, the signal conversion means 31X receives the input S
_{Receives iin} (X) (i = 1 to N) and outputs S _jout (X)
(J = 1 to K) is output. The correction means 32X uses the signal S
_The error signal δ is received by receiving _iin (X) and the signal S _jout (X).
Wait until _j (X) (j = 1 to K) is input. The same processing is performed in the signal processing means 34Y and 34Z, and the final output _Shout (Z) from the signal converting means 31Z.
(H = 1 to M) is output. Final output _Shout (Z)
Is also sent to the error calculation means 33. Error calculation means 33
, The error from the ideal output T (T1, ..., TM) is calculated based on the squared error evaluation function COST (Equation 4), and the error signal δ _h (Z) is sent to the correction means 32Z. Be done.

[0020]

[Equation 1]

However, η is a parameter that determines the learning speed of the multilayer perceptron. Next, when the evaluation function is a square error, the error signal is δh (Z) = − η · (S _hout (Z) −T _h ) (Equation 5). The correction unit 32Z calculates the correction amount ΔW (Z) of the conversion parameter of the signal conversion unit 31Z according to the procedure described above, calculates the error signal to be sent to the correction unit 32Y based on (Equation 6), and the correction signal ΔW (Z) is sent to the signal converting means 31Z, and the error signal δ (Y) is corrected by the correcting means 32.
Send to Y. The signal conversion means 31Z uses the correction signal ΔW (Z).
Modify internal parameters based on. The error signal δ (Y) is given by (Equation 6).

[0022]

[Equation 2]

[0023] Here, W _ij (Z) signal converting means 31Z
Is a conversion parameter of the pseudo synapse coupling converter of. Hereinafter, similar processing is performed in the signal processing means 34X and 34Y. By repeating the above procedure called learning, the multi-layer perceptron produces an output that closely approximates the ideal output T when given an input. In the above description, the three-stage multi-layer perceptron is used, but this may be any number of stages. In addition, reference 1
The modification method of the conversion parameter h of the non-linear conversion means in the signal conversion means and the method of accelerating learning known as the inertia term are omitted for simplification of the description, but this omission is described below. It does not bind the invention.

In this way, the neural network model means learns the relationship between environmental data (room temperature, set temperature, sitting state, etc.), control data, and surface temperature data, and a control method that is not easy to describe by simple rules. Can be expressed in a natural way. In this embodiment, the surface temperature estimating means 13 is configured by incorporating the information thus obtained.
Specifically, the surface temperature estimation means 13 is configured by using only the signal conversion means 31X, 31Y, 31Z of the multilayer perceptron after sufficiently learning as a neural network schematic means. That is, the temperature detecting means 5 is connected to the neural network model means.
Temperature information, set temperature information obtained from the temperature setting means 6 as physical information that affects heat generation on the surface of the toilet seat and can be actually measured, room temperature information of the room temperature detecting means 9, and time measuring means 10
6 information of the elapsed time information after power-on obtained from the power-on, the current duty ratio information obtained from the duty ratio detecting means 11, and the seating state information obtained from the seating detecting means 12, and the surface of the toilet seat body 1 as an ideal output. Temperature information is input and learned, and signal conversion means 31X, 3 in the neural network model means
1Y and 31Z are established, and they are incorporated in the surface temperature estimation means 13 as a neural network schematic means.

Next, the operation will be described based on the circuit block diagram shown in FIG. First, the temperature setting means 6 sets the set temperature and the power is turned on. The temperature setting information is input to the surface temperature estimation means 13 via the control means 7. The control means 7 outputs a signal to start timing to the timing means 10 and outputs an energization on (relay on) signal to the energization control means 4 to cause the heating element 2 to generate heat. The energization rate detection means 11 receives the state of the energization control means 4 (ON / OFF state of the relay) from the control means 7 and the timing signal from the timing means 10, and calculates the energization rate to the heating element 2 every moment. Then, the information is output to the surface temperature estimating means 13.
The timing information of the timing means 10 is input to the surface temperature estimation means 13 via the control means 7. The temperature information of the heating element 2 is input to the control means 7 from the temperature detection means 5 via the temperature detection body 3 every moment, and the control means 7 outputs the current temperature information to the surface temperature estimation means 13. The seating detection means 12 also outputs seating state information to the surface temperature estimation means 13 via the control means 7. The set temperature information of the temperature setting means 6 is also input to the surface temperature estimating means 13 via the control means 7. Further, the room temperature information from the room temperature detecting means 9 is AD-converted and input to the control means 7 and the surface temperature estimating means 13. The surface temperature estimation means 13 is
Based on these input signals and information, the surface temperature of the toilet seat body 1 is estimated every moment, and the information is output to the control means 7. The control means 7 controls the energization control means 4 (on / off control) so as to maintain the set temperature based on the estimated surface temperature information.

Further, FIG. 7 illustrates a method of calculating a duty ratio.
It is a figure for, and shows the relay state of the energization control means 4.
ing. In this embodiment, time t_pThe duty factor at
Tick t _pThe previous relay is on for t_pon， Off period
T_poffThen, it was calculated by (Equation 8).

T _pon / (t _pon + t _poff ) (Equation 8) In the present embodiment, the duty ratio is determined by the duty ratio as in (Equation 8), but the method is not limited to this method and the power supply is not limited. It may be the cumulative energization rate from the time of input. Further, the control means 7, the timing means 10, the duty ratio detection means 11,
The surface temperature estimating means 13 are all composed of 1-bit microcomputers, but it is of course possible to form them by one microcomputer. Further, the surface temperature estimation means 13 has temperature information of the temperature detection means 5, and set temperature information of the temperature setting means 6 and room temperature information of the room temperature detection means 9 as physical information that affects the heat generation of the toilet seat surface and can be actually measured. Six pieces of information, namely, elapsed time information from when the power is turned on, which is obtained from the time counting means 10, current duty ratio information obtained from the duty ratio detecting means 11, and seating state information of the seating detecting means 12, are input, but this limitation is not provided. Does not restrict the present invention, and the estimation accuracy of the surface temperature can be further improved depending on the configuration of the physical quantity measuring means 8.

As described above, according to the present embodiment, the surface temperature estimating means incorporating the neural network schematic means having a plurality of fixed coupling weight coefficients already learned under the environment of use is provided. Therefore, in the environment where the toilet device is used, optimal heating that fits a human can be realized.

[0029]

As is apparent from the above embodiments, according to the present invention, temperature detecting means for detecting the temperature of the heating element of the toilet seat body, energization control means for controlling the energization of the heating element, and A physical quantity measuring means for measuring and setting a physical quantity that affects the heat generation of the toilet seat body; a temperature detecting means; a surface temperature estimating means for estimating the surface temperature of the toilet seat body based on the output of the physical quantity measuring means; and the surface temperature. It is possible to realize optimal heating corresponding to a change in toilet seat surface temperature due to a change in environment such as a change in room temperature or a user's seat, which is composed of control means for controlling the energization control means based on the output of the estimation means.

The surface temperature estimating means has a plurality of fixed connection weighting coefficients for estimating the surface temperature of the toilet seat body, which are obtained by modeling and learning a neural network composed of a plurality of neural elements. Since it has a neural network schematic means or a hierarchical neural network schematic means constructed by combining a number of layers composed of a plurality of neural elements, it is possible to accurately estimate the toilet seat surface temperature, Optimal heating that fits in can be realized.

[Brief description of drawings]

FIG. 1 is a circuit block diagram of a toilet device according to an embodiment of the present invention.

FIG. 2 is a partially cutaway sectional view of a toilet seat body of the toilet device.

FIG. 3 is a conceptual diagram of a neural element which is a constituent unit of the neural network schematic means used in the toilet device.

FIG. 4 is a conceptual diagram of a signal conversion unit composed of neural elements used in the toilet device.

FIG. 5 is a block diagram of a signal processing unit that employs an error backpropagation method as a learning algorithm used in the toilet device.

FIG. 6 is a block diagram showing a configuration of a multilayer perceptron using a neural network schematic means used in the toilet device.

FIG. 7 is a diagram for explaining a method of calculating a duty ratio of the toilet device.

FIG. 8 is a configuration diagram of a conventional toilet device.

FIG. 9: Characteristic diagram of toilet seat surface temperature change due to difference in room temperature of the toilet device

FIG. 10 is a change characteristic diagram of the toilet seat surface temperature and the toilet seat internal temperature when the toilet device changes in room temperature.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Toilet seat main body 2 Heating element 3 Temperature detection body 4 Energization control means 5 Temperature detection means 7 Control means 8 Physical quantity measurement means 13 Surface temperature estimation means

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Nakason Son 10-1 Higashisanda, Tama-ku, Kawasaki-shi, Kanagawa Matsushita Giken Co., Ltd.

Claims (3)

[Claims] 1. A toilet seat body provided with a heating element and a temperature detecting element, temperature detecting means for detecting the temperature of the heating element via the temperature detecting element, and energization control for controlling energization to the heating element. Means, a physical quantity measuring means for measuring and setting a physical quantity that influences heat generation of the toilet seat body, a temperature detecting means, and a surface temperature estimating means for estimating the surface temperature of the toilet seat body based on the output of the physical quantity measuring means. A toilet device comprising: a control unit that controls the energization control unit based on an output of the surface temperature estimation unit. 2. The surface temperature estimating means has a plurality of fixed connection weighting factors for estimating the surface temperature of the toilet seat body, which are obtained by learning by modeling a neural network composed of a plurality of neural elements. The toilet device according to claim 1, further comprising a neural network schematic unit. 3. The toilet device according to claim 1, wherein the surface temperature estimating means has a hierarchical neural network schematic means constructed by combining a number of layers each composed of a plurality of neural elements.