JP2936838B2 - kitchenware - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a cooking appliance for automatic cooking in a microwave oven, a gas oven, a roaster or the like.

[0002]

2. Description of the Related Art Conventionally, this type of cooking utensil (here, roaster) has been configured as shown in FIG. Less than,
The configuration will be described.

[0003] As shown in the figure, a cooking utensil 1 is composed of a heating chamber 2 for holding the food, a heating supply means (heater) 3 for heating the food, a thermistor for detecting the internal temperature of the heating chamber 2 and the like. A temperature detecting means 4 and a control means 5 for controlling the heating supply means 3 based on information from the temperature detecting means 4. In order to perform automatic cooking with such a configuration, it is necessary to know the weight of the food, the initial temperature, and the like. For this purpose, the output voltage gradient of the temperature detecting means 4 is measured for several minutes after the power is turned on. If the gradient is steep, it is determined that the weight of the food is light, and if the gradient is gentle, it is determined that the weight is large. Is set as the optimal cooking time. FIG. 12 shows the output voltage characteristics of the temperature detecting means 4. FIG. 12A shows a light weight, and FIG. 12B shows a heavy weight. He had done a lot of cooking experiments and determined the constants.

[0004]

In such a conventional cooking utensil (here, roaster), a gradient of an ambient temperature in a heating chamber is detected, and a cooking object (for example, roaster) is detected based on the detected gradient.
Since the cooking time was determined based on the weight of the grilled fish, there was considerable variation in the completion of the cooking. For example, the initial temperature in the heating chamber is not always low, and if cooking is performed immediately after cooking, the initial temperature in the heating chamber becomes very high. In this case, when heavy food is cooked, the output voltage characteristic of the temperature detecting means 4 is as shown in FIG.
As shown in FIG. 3, the temperature in the heating chamber drops momentarily. This is because the temperature in the heating chamber is absorbed by the cooked food because the temperature in the heating chamber is high even when cooking is started. In such a case, it was difficult to determine the optimum cooking time by the above-mentioned method. Further, since the heating supply means 3 is a heater, fluctuations in the commercial power supply voltage have a considerable effect on the completion of cooking. In other words, the completion of the cooking varies considerably depending on the environment at the time of starting the cooking (the type of the food, the initial temperature in the heating chamber, the initial temperature of the food, the power supply voltage, etc.). Further, with respect to the burning of fish and the like, the baked condition of the surface is also important, but the temperature rise inside the fish is also 6%.
0 ° C to 70 ° C is considered to be the best. In view of such a situation, there is a problem that it is very difficult to detect the completion of cooking in terms of the degree of burning of the surface and an increase in the internal temperature.

[0005] The present invention solves the above-mentioned problems, and estimates the temperature of a cooking object in real time by estimating the temperature of the cooking object from the environmental physical quantities in the heating chamber that can be actually measured and detected, and the physical quantities unique to the cooking object. The purpose is to detect the completion indirectly.

[0006]

SUMMARY OF THE INVENTION In order to achieve the above object, the present invention provides a heating chamber for storing foods for cooking, a heating supply means for heating the foods, and an environment in the heating chamber. Environmental physical quantity detecting means for detecting the cooking property specific physical quantity detecting means for detecting the specific physical quantity of the food,
The surface temperature of the food, the central temperature, based on the outputs of the environmental physical quantity detection means and the food specific physical quantity detection means,
Temperature estimation means for estimating at least one of the back surface temperatures, and control means for controlling the heating supply means based on the output of the temperature estimation means, wherein the temperature estimation means comprises a plurality of neural elements. There is provided a hierarchical neural network model having a plurality of connection weight coefficients of a fixed neural network for estimating a temperature of a food obtained by a method simulating a configured neural network.

[0007]

According to the present invention, by actually inputting the environmental information in the heating chamber from the environmental physical quantity detecting means and the unique physical information from the cooked unique physical quantity detecting means to the temperature estimating means, the present invention makes it possible to actually cook the food. Temperature estimating means having a neural network model means which learns all the actual cooking environment and has as a connection weight coefficient fixed inside, at least one of the surface temperature, the center temperature, and the back surface temperature of the food. Estimate every moment. The control means controls the heating supply means (heater in the case of an electric roaster) based on the output of the temperature estimating means, and indirectly detects a rise in the temperature of the food, thereby acting to recognize the completion. I do.

[0008]

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

In this embodiment, an example in which the present invention is applied to an electric roaster for baking fish and the like as a cooking utensil will be described. FIG.
As shown in (1), the environmental physical quantity detecting means 6 detects the environment in the heating chamber. In this embodiment, the temperature of the atmosphere in the heating chamber is detected, and is constituted by a thermistor or the like. The voltage level detecting means 7 detects the voltage level of the commercial power supply voltage. The timer 8 counts the time from when the power is turned on. The operation means 9 includes a category selection key 10 for selecting a category of the food and a cooking start key 11 for starting / stopping cooking. The cooking-specific physical quantity detecting means 12 detects a physical quantity unique to the cooking product. In the present embodiment, the cooking-specific physical quantity detecting means 12 detects the weight of the cooking product and is configured by a weight sensor (strain gauge) or the like. The weight of the cooked food changes from moment to moment because steam is generated with heating. The temperature estimating means 13 estimates the surface temperature, the center temperature, and the back surface temperature of the food based on the outputs of the environmental physical quantity detecting means 6, the cooking specific physical quantity detecting means 12, the voltage level detecting means 7, the timing means 8, and the category selection key 10. The control means 5 controls the heating supply means 3 based on the output of the temperature estimating means 13. The heating supply means 3 is a heater and is provided in the heating chamber 2. Numeral 14 denotes a display means for displaying the remaining time of cooking, etc., which comprises a fluorescent display tube. A / D converters 15, 16, and 17 convert the outputs of the environmental physical quantity detector 6, the voltage level detector 7, and the cooking specific physical quantity detector 12 into digital signals. FIG. 2 shows the configuration of the display unit and the operation unit.

[0010] As means constituting the temperature estimating means 13, the solution method used in the conventional control method cannot be applied, so that the temperature estimating means 13 is constituted by a method simulating a neural network which is optimal as a multidimensional information processing method. I have. In the method simulating the neural network, a method of using a plurality of connection weighting factors of the neural network as a fixed table for estimating the temperature of the food (surface temperature, center temperature, back surface temperature) and a learning function are left. There are ways to adapt to the environment and the user. In the present embodiment, there is provided a temperature estimating unit 13 having a neural network model having a fixed connection weight coefficient therein for estimating the temperature of a food obtained by a method imitating a neural network.

Factors that affect the quality of the cooked food include the initial temperature in the heating chamber, the initial temperature of the cooked food, the type (category) of the cooked food, and the voltage level of the commercial power supply voltage. The quality varies greatly depending on those factors.

[0012] The connection weighting factor fixed in the neural network for estimating the temperature of the food is determined by the surface temperature of the food when cooked in an actual cooking environment (an environment in which various factors described above are combined). , The center temperature, the backside temperature, the atmosphere temperature in the heating chamber, and the change in weight of the food are collected. The environmental data, the atmosphere temperature data in the heating chamber, the weight change data, and the temperature of the food are collected. The correlation with the front, center and back data can be obtained by learning the neural network model. As a schematic means of a neural network to be used, reference 1 (DE.
Ramelhart and two other authors, translated by Shunichi Amari "PDP Model"
Sangyo Tosho, 1989), Reference 2 (Kaoru Nakano et al., "Basics of Neurocomputer", published by Corona Co., Ltd.,
P102, 1990) and JP-B-63-55106. Hereinafter, the configuration and operation of specific neural network model means will be described using a multilayer perceptron using an error back propagation method as an example of the most well-known learning algorithm described in Document 1.

FIG. 3 is a conceptual diagram of a neural element which is a constituent unit of the neural network schematic means. In FIG.
N is a pseudo-synaptic connection converter that simulates a synaptic connection of a nerve, and 2a is a pseudo-synaptic connection converter 21-2N
2b is a set nonlinear function, for example, a sigmoid function with a threshold value h, f (y, h) = 1 / (1 + exp (−y + h)) (Equation 1) ) Is a nonlinear converter for nonlinearly converting the output of the adder 2a. Although not shown for simplicity of the drawing, an input line for receiving a correction signal from the correction means is connected to the pseudo-synaptic coupling converters 21 to 2N and the nonlinear converter 2b. Further, the pseudo synapse connection converters 21 to 2N serve as connection weight coefficients of the neural network model. 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 in the signal processing mode will be described. The neural element has N inputs X1 to X
n and outputs one output. i-th input signal Xi
Is the i-th pseudo-synaptic coupling converter 2 indicated by a square.
In i, it is converted to Wi · Xi. N signals W1.X1 to N1 converted by the pseudo-synaptic coupling converters 21 to 2N
Wn · Xn enters the adder 2a, and the addition result y is sent to the non-linear converter 2b, and becomes the final output f (y, h). Next, the operation in the learning mode will be described. In the learning mode, the conversion parameters W1 to Wn and h of the pseudo-synaptic coupling converters 21 to 2N and the non-linear converter 2b are received, and correction signals representing the conversion parameter correction amounts △ W1 to △ Wn and 修正 h from the correction unit are received. , Wi + △ Wi; i = 1, 2,..., Nh + （h (Equation 2).

FIG. 4 is a conceptual diagram of a signal conversion means in which four neural elements are connected in parallel. Needless to say, the following description does not specify the number of neural elements constituting the signal conversion means as four. In FIG. 4, reference numerals 211 to 244 denote pseudo-synaptic coupling converters,
Reference numerals 201 to 204 denote add-nonlinear converters that combine the adder 2a and the non-linear converter 2b described in FIG. In FIG. 4, as in FIG. 3, the illustration is omitted because it becomes complicated, but the input lines receiving the correction signal from the correction means are connected to the pseudo-synaptic coupling converters 211 to 244 and the addition nonlinear converter 20.
1 to 204 are connected. The pseudo synapse connection converters 211 to 244 also become connection weight coefficients. As for 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 backpropagation method is adopted as the learning algorithm. Reference numeral 31 denotes the above-described signal conversion means. However,
Here, M neural elements receiving N inputs are arranged in parallel. Reference numeral 32 denotes a correction unit that calculates a correction amount of the signal conversion unit 31 in the learning mode. Hereinafter, an operation when learning of the signal processing unit is performed will be described with reference to FIG. The signal conversion means 31 has N inputs S
_In (X), M outputs S _out (X) are output.
The correction means 32 includes an input signal S _in (X) and an output signal S _out
(X), and waits until M error signals δ _i (X) are input from the error calculation means or the signal conversion means at the subsequent stage. The error signal δ _i (X) is input and the correction amount is represented by ΔW _ij = δ _i (X) · S _iout (X) · (1−S _iout (X)) · S _jin (X) (i = 1 to N , J = 1 to M) (Equation 3), and sends the correction signal to the signal conversion means 31. The signal conversion means 31 corrects the conversion parameters of the internal nerve elements according to the learning mode described above.

FIG. 6 is a block diagram showing the configuration 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.
2Z is a correction means, and 33 is an error calculation means. The operation of the multilayer perceptron configured as described above will be described with reference to FIG. Signal processing means 3
4X, the signal conversion means 31X receives the input S
_iin (X) (i = 1 to N) and output _Sjout (X)
(J = 1 to k) is output. The correction means 32X outputs the signal S
_iin (X) and the signal _Sjout (X), and the error signal δ
Wait until _j (X) (j = 1 to k) is input. Hereinafter, similar processing is performed in the signal processing units 34Y and 34Z, and the final output S _hout (Z) is output from the signal conversion unit 31Z.
(H = 1 to M) are output. Final output S _hout (Z)
Is also sent to the error calculation means 33. Error calculation means 33
, An error from the ideal output T (T1,..., TM) is calculated based on the square error evaluation function COST (Equation 4), and the error signal δ _h (Z) is corrected. 32Z
Sent to

[0018]

(Equation 1)

Here, 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 △ W (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 corrects the error signal. The signal △ W (Z) is sent to the signal converting means 31Z, and the error signal δ (Y) is
Send to Y The signal conversion means 31Z outputs the correction signal △ W (Z)
Modify internal parameters based on. Note that the error signal δ (Y) is given by (Equation 6).

[0020]

(Equation 2)

Here, W _ij (Z) is the signal conversion means 31Z.
Is a conversion parameter of the pseudo-synaptic coupling converter. Hereinafter, similar processing is performed in the signal processing units 34X and 34Y. By repeatedly performing the above procedure called learning, the multilayer perceptron, when given an input, outputs an output that approximates the ideal output T well. In the above description, a three-stage multilayer perceptron is used, but the number of stages may be any. Reference 1
The method for correcting the conversion parameter h of the non-linear conversion means in the signal conversion means and the method for speeding up learning, which is known as an inertia term, are omitted for simplicity of description. It is not binding on the invention.

In this way, the neural network model means can provide the environment data (such as the initial temperature in the heating chamber, the commercial power supply voltage level, the type of the food, the initial temperature of the food, etc.) and the atmospheric temperature data in the heating chamber when cooking. By learning the relationship between the weight change data of the food and the temperature (front, center, back) data of the food, it is possible to express in a natural manner a control method that is not easy to describe with simple rules. In this embodiment, the temperature estimating means 13 is configured by incorporating the information thus obtained. Specifically, the signal conversion means 31X, 31Y of the multi-layer perceptron after sufficient learning is completed.
The temperature estimating means 13 is constituted by using only 31Z as the neural network schematic means. The data actually learned will be described.

FIG. 7 shows the characteristics when cooking is performed when the initial temperature of the heating chamber 2 is low, the commercial power supply voltage is 100 V, the type of food is one horse mackerel, and the initial temperature of the food is about 10 ° C. It was done. FIG. 7A shows the environmental physical quantity detecting means 6.
7 (b) shows the change in weight of the food, FIG. 7 (c) shows the surface temperature of the food, FIG. 7 (d) shows the center temperature of the food, FIG. 7E shows a change in the back surface temperature of the food. The temperature of the food is measured using a thermocouple or the like. FIG. 8 shows the characteristics when cooking was performed when the initial temperature of the heating chamber 2 was high, the commercial power supply voltage was 100 V, the type of food was one horse mackerel, and the initial temperature of the food was about 10 ° C. is there. FIG. 9 shows the heating chamber 2
The initial temperature is low, the commercial power supply voltage is 100 V, the type of food is four horse mackerels, and the initial temperature of the food is about 10 ° C., showing the characteristics when cooking. FIG. 10 shows characteristics when cooking was performed when the initial temperature of the heating chamber 2 was high, the commercial power supply voltage was 100 V, the type of food was four horse mackerels, and the initial temperature of the food was about 10 ° C. is there.

FIGS. 8 (a) to 8 (e), FIGS. 9 (a) to 9 (e), and FIGS. 10 (a) to 10 (e) show FIG. 7 (a).
7 to (e). It can be seen that the output voltage change of the environmental physical quantity detecting means 6 (atmospheric temperature in the heating chamber) and the output voltage change of the cooking-specific physical quantity detecting means 12 differ depending on the initial temperature in the heating chamber and the amount of the food. Similarly, when the power supply voltage is changed or the type of food is changed, the output changes again. Such an experiment was similarly performed for all combinations of environments when actually cooking. Then, the experimental data was input to the neural network model means for learning. In other words, the neural network schematic means sends the ambient temperature information in the heating chamber of the environmental physical quantity detecting means 6, the atmospheric temperature information one minute before the present time as the ambient temperature gradient information, and the cooking specific physical quantity detecting means 12. Weight information, weight data one minute before the present time as the weight change information, commercial power supply voltage level information of the voltage level detecting means 7, elapsed time information from power-on obtained by the time measuring means 8, and a category selection key 7 information of category information obtained from 10 and three information of surface temperature information, center temperature information, and back surface temperature information of the food as an ideal output are input and learned, and signal conversion means 31X in the neural network model means are input. 31Y and 31Z are established, and they are incorporated in the temperature estimating means 13 as a schematic means of a neural network.

Next, the operation will be described with reference to the block diagram shown in FIG. First, put the food in the heating room,
The cooking category is selected by the category selection key 10 in the operation means 9. Then, cooking is started by the cooking start key 11. The category information is input to the temperature estimating means 13 via the control means 5. The control means 5 outputs a signal to start time measurement to the time measurement means 8 and outputs a heating start signal to cause the heating supply means 3 to generate heat. The timing information of the timing means 8 is input to the temperature estimating means 13. The output of the environmental physical quantity detecting means 6 is digitally converted by the A / D converting means 15 and the physical physical information (atmospheric temperature information) in the heating chamber is input to the temperature estimating means 13 every moment. The voltage level information of the commercial power supply voltage from the voltage level means 7 is digitally converted by the AD conversion means 16 and input to the temperature estimation means 13. Also, the weight information from the cooking specific physical quantity detecting means 12 is transmitted to the A / D converting means 1.
The digitally converted data is input to the temperature estimating means 13 in FIG. The temperature estimating means 13 calculates these input signals
Based on the information, the surface temperature, center temperature, and back surface temperature of the food are estimated every moment, and the information is output to the control means 5. The control means 5 operates to control the heating supply means 3 based on the estimated temperature information.

Although the control means 5, the time measuring means 8 and the temperature estimating means 13 are all constituted by 4-bit microcomputers, they can be constituted by a single microcomputer. The temperature estimating means 1
3 includes temperature gradient information of the environmental physical quantity detecting means 6 (two pieces of information at the present time and one minute before) and a cooking-specific physical quantity detecting means 12.
Weight information (two pieces of information of the current time and one minute before), the voltage level information of the commercial power supply voltage obtained by the voltage level detecting means 7, the elapsed time information from power-on obtained by the timing means 8, and a category selection key Although seven pieces of information of the category information of the food obtained from 10 are input, this limitation does not restrict the present invention. Although the ambient temperature information was used as the environmental physical quantity information, smoke information, burnt color information, humidity information, and steam information can also be applied, and a shape and the like can be applied in addition to the weight information as the cooking-specific physical quantity. The estimation accuracy is further improved by combining. Further, in this embodiment, the electric roaster was used as the cooking utensil, but it may be a microwave oven or a gas oven.
In a microwave oven, it seems to be optimal when thawing the food. That is, since the temperature of the cooked food can be estimated, the cooking should be finished around the vicinity where the phase transition from solid (ice) to liquid (water) occurs (around 0 ° C.).
At this time, the environmental physical information may be an ambient temperature,
The information on the amount of electric wave absorption (electrolytic strength) of the cooked food is optimal.

As described above, according to the present embodiment, temperature estimation incorporating neural network model means having a plurality of fixed connection weighting factors of a neural network already learned in an environment of a heating room where cooking is actually performed. Since it has a configuration with means,
The completed state of the cooked food can be detected based on the front surface temperature, the center temperature, and the back surface temperature, so that the cooked state can be further improved as compared with the related art, which is optimal for automatic cooking.

[0028]

As is apparent from the above embodiments, according to the present invention, a heating chamber for storing foods for cooking,
Heating supply means for heating the food; environmental physical quantity detection means for detecting an environment in the heating chamber; cooking specific physical quantity detection means for detecting a unique physical quantity of the food; the environmental physical quantity detection means and the cooking A temperature estimating means for estimating the temperature of the food based on the output of the physical characteristic physical quantity detecting means, and a control means for controlling the heating and supplying means based on the output of the temperature estimating means, so that the finished state of the food is determined. For recognition, the actual temperature of the food can be detected indirectly. Therefore, it is possible to improve the cooking completion state as compared with the conventional one in which the optimum cooking time is determined from the gradient such as the ambient temperature.

Further, the temperature estimating means includes: a surface temperature of the food;
Since at least one of the center temperature and the back surface temperature is estimated, the overall finished state from the front surface to the inside of the food can be understood.

Further, the temperature estimating means is a fixed neural network for estimating the temperature (front, center, back surface temperature) of the food obtained by a method simulating a neural network composed of a plurality of neural elements. Since it has a neural network model having a plurality of connection weighting factors therein, or has a hierarchical neural network model which is constructed by combining layers composed of a plurality of neural elements in multiple layers, Regardless of the initial temperature of the heating chamber, the initial temperature of the food, the amount of the food, and the like, the temperature of the food can be estimated and automatic cooking can be performed.

[Brief description of the drawings]

FIG. 1 is a block diagram showing the configuration of a cooking appliance according to one embodiment of the present invention.

FIG. 2 is a configuration diagram of an operation unit and a display unit used in the cooking appliance.

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

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

FIG. 5 is a block diagram of a signal processing unit employing an error back propagation method as a learning algorithm used in the cooking appliance.

FIG. 6 is a block diagram showing a configuration of a multilayer perceptron using a neural network model used in the cooking appliance.

FIGS. 7A to 7E show examples of experimental data of the cooking utensil.

8 (a) to 8 (e) are diagrams showing other examples of experimental data of the cooking utensil.

9 (a) to 9 (e) are views showing other examples of experimental data of the cooking utensil.

10 (a) to 10 (e) are diagrams showing other examples of experimental data of the cooking utensil.

FIG. 11 is a configuration block diagram of a conventional cooking appliance.

12 (a) and 12 (b) are diagrams showing examples of experimental data of a conventional cooking appliance.

FIG. 13 is a diagram showing another example of experimental data of a conventional cooking appliance.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Cooking appliance 2 Heating chamber 3 Heat supply means 5 Control means 6 Environmental physical quantity detection means 7 Cooking thing specific physical quantity detection means 13 Temperature estimation means

Claims (4)

(57) [Claims] 1. A heating chamber for storing cooked food for cooking, heating supply means for heating the cooked food, environmental physical quantity detecting means for detecting an environment of the heating chamber, and a physical physical quantity of the cooked food. A temperature estimating unit configured to detect a cooking-specific physical quantity detecting means, an environmental physical quantity detecting means, and a temperature of the cooking product based on an output of the cooking-specific physical quantity detecting means during heating cooking; Means,
A cooking device comprising: control means for controlling the heating supply means based on the output of the temperature estimating means. 2. The cooking appliance according to claim 1, further comprising temperature estimating means for estimating at least one of a front surface temperature, a center temperature, and a back surface temperature of the food. 3. The neural network constructing means is obtained by a method simulating a neural network composed of a plurality of neural elements .
The cooking appliance according to claim 1, wherein the cooking appliance has a plurality of connection weighting factors therein. 4. The cooking utensil according to claim 1, wherein the neural network model means has a hierarchical structure in which a layer composed of a plurality of neural elements is constructed by combining multiple layers.