JPH05113220A - Cooking equipment - Google Patents

Abstract

PURPOSE:To improve a finished state of cooked item and realize an automatic cooking by a method wherein temperatures of the cooked item (at its surface, central part and rear surface, respectively) are estimated in a real time by a temperature estimating means. CONSTITUTION:A cooking equipment is comprised of a heating chamber 2 for storing a cooked item to be cooked, a heating and supplying means 3 for heating the cooked item, a cooked item specific physical amount detecting means 6 for detecting the specific physical amount of the cooked item, a temperature estimating means 12 for estimating temperature of the cooked item in response to an output of the cooked item specific physical amount detecting means 6, and a control means 5 for controlling the heating and supplying means 3 in response to an output of the temperature estimating means 12. The temperature estimating means 12 is constructed such that it has a neuron network model means having a plurality of connection weighing coefficient fixed while its studying under a cooking environment for its practical cooking has already been performed, thereby the temperature estimation of the cooked item (its surface, central part and rear surface temperatures, respectively) irrespective of such items as an initial temperature within the heating chamber, an initial temperature of the cooked item and an amount of the cooked item and the like can be carried out and so an automatic cooking having a better finished state is realized.

Description

Detailed Description of the Invention

[0001]

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

[0002]

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

As shown in the figure, a cooking utensil 1 is composed of a heating chamber 2 in which a food is put, 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. The temperature detecting means 4 and the control means 5 for controlling the heating supply means 3 based on the information from the temperature detecting means 4. In order to automatically cook with such a structure, it is necessary to know the weight of the food, the initial temperature, and the like. Therefore, the output voltage gradient of the temperature detecting means 4 is measured for several minutes after the power is turned on, and if the gradient is steep, the weight of the cooked food is light,
If the gradient is gentle, it is determined that the weight is large, and the time obtained by multiplying the voltage gradient by a constant K is set as the optimum cooking time. The output voltage characteristic of the temperature detecting means 4 is shown in FIG. FIG. 12A shows a light weight, and FIG. 12B shows a heavy weight. And I did a lot of cooking experiments and decided the constant.

[0004]

In such a conventional cooking utensil (here, a roaster), the gradient of the ambient temperature in the heating chamber is detected, and the cooking product (for example,
The cooking time was decided based on the weight of the (fried fish), so there was considerable variation in the completion of cooking. For example, the initial temperature in the heating chamber is not always low, and when cooking is performed immediately after finishing cooking, the initial temperature in the heating chamber becomes very high. In this case, when a heavy food is cooked, the output voltage characteristic of the temperature detecting means 4 is shown in FIG.
The temperature inside the heating chamber drops for a moment. This is because the temperature inside the heating chamber is absorbed by the food because the temperature inside 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 method described above. Further, since the heating supply means 3 is a heater, the fluctuation of the commercial power supply voltage considerably affects the completion of cooking. In other words, the completion of cooking varies considerably depending on the environment at the time of starting cooking (type of food, initial temperature in heating chamber, initial temperature of food, power supply voltage, etc.). In addition, when it comes to grilling fish, it is important that the surface is baked, but the temperature inside the fish will rise by 6
0 ° C to 70 ° C is the best. In consideration of such a situation, there is a problem that it is very difficult to detect the completion of cooking in terms of the surface burnt condition and the internal temperature rise.

The present invention solves the above problems and indirectly detects the completion of a cooked product by estimating the temperature of the cooked product in real time with a physical quantity peculiar to the cooked product that can be actually measured and detected. The purpose is to

[0006]

In order to achieve the above-mentioned object, the present invention provides a heating chamber for storing a cooking product for cooking, a heating supply means for heating the cooking product, and an inherent cooking product. A cooking product-specific physical quantity detection means for detecting a physical quantity,
Temperature estimation means for estimating at least one of the surface temperature, the center temperature, and the back surface temperature of the cooked food based on the output of the cooked product physical quantity detection means, and the heating supply based on the output of the temperature estimation means. The temperature estimating means comprises a plurality of fixed neural networks for estimating the temperature of the cooked food obtained by a method simulating a neural network composed of a plurality of neural elements. It has a hierarchical neural network schematic means having the connection weight coefficient of the inside.

[0007]

According to the present invention, all the actual cooking environments to be actually cooked are learned by inputting the unique physical information unique to the cooked food from the cooked food unique physical quantity detecting means to the temperature estimating means by the above problem solving means. The temperature estimating means having a neural network model means having a fixed connection weighting coefficient internally estimates at least one of the surface temperature, the center temperature and the back surface temperature of the cooking product moment by moment. The control means controls the heating supply means (heater in the electric roaster) based on the output of the temperature estimation means, and indirectly detects the temperature rise of the cooked product, thereby recognizing the completion. To do.

[0008]

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.

In this embodiment, an example in which an electric roaster for grilling fish etc. is applied as a cooking tool will be described. Figure 1
As shown in FIG. 5, the cooking product-specific physical quantity detection unit 6 detects a physical quantity unique to the cooking product. In this embodiment, a weight sensor (strain gauge) is used to detect the weight of the food.
Etc. The weight of the cooked food changes with time because steam is generated as it is heated. The voltage level detecting means 7 detects the voltage level of the commercial power supply voltage. The timekeeping means 8 counts the time since the power was turned on. The operating means 9 comprises a category selection key 10 for selecting a category of food and a cooking start key 11 for starting and stopping cooking. The temperature estimating means 12 is a cooking product-specific physical quantity detecting means 6, a voltage level detecting means 7, a clocking means 8,
Based on the output of the category selection key 10, the surface temperature, the center temperature, and the back surface temperature of the cooking product are estimated, and the control means 5 outputs the heating supply means 3 based on the output of the temperature estimation means 12.
To control. The heating supply means 3 is a heater and is arranged in the heating chamber 2. Further, reference numeral 13 is a display means for displaying the remaining time of cooking and the like, which comprises a fluorescent display tube. Further, 14 and 15 are A / D conversion means, which convert the outputs of the cooking product specific physical quantity detection means 6 and the voltage level detection means 7 into digital signals. FIG. 2 shows the configuration of the display unit and the operation unit.

Since the solving means used in the conventional control method cannot be applied to the means constituting the temperature estimating means 12, the means for simulating an optimum neural network as a multidimensional information processing method is used. There is. In the method that imitates the neural network, a method of using a plurality of connection weight coefficients of the neural network for estimating the temperature (surface temperature, central temperature, back surface temperature) of the cooked food as a fixed table and leaving the learning function There are ways to adapt to the environment and users. The present embodiment is provided with a temperature estimating means 12 having a neural network model means having therein a fixed coupling weight coefficient for estimating the temperature of a food product obtained by a method simulating a neural network.

Factors that affect the completion 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, the voltage level of the commercial power supply voltage, and the like. The finished product fluctuates greatly due to these factors.

The fixed weighting coefficient fixed in the neural network for estimating the temperature of the cooked food is the surface temperature of the cooked food when cooked in the actual cooking environment (environment in which various factors described above are combined). , Data on how the center temperature, backside temperature, and ambient temperature in the heating chamber change, and the correlation between the environmental data, the ambient temperature data in the heating chamber, and the temperature of the cooked food (front, center, backside) Can be obtained by training the neural network model means. As a neural network schematic means to be used,
Reference 1 (DE Lamelhardt et al. 2 authors, Shunichi Amari supervised translation "PDP Model" Sangyo Tosho, 1989), Reference 2 (Kaoru Nakano et al. 7 authors "Basics of Neurocomputer")
Published by Corona Publishing Co., Ltd., P102, 1990), Shokoku Sho 6
There is one disclosed in Japanese Patent Laid-Open No. 3-55106. 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, and the correction signals representing the correction parameter correction amounts ΔW1 to ΔWn and Δh are received from the correction means. , Wi + ΔWi; i = 1, 2, ..., N h + Δh (Equation 2)

FIG. 4 is a conceptual diagram of a signal converting means constituted by connecting four neural elements in parallel. Needless to say, the following description does not specify that the number of neural elements constituting this signal converting means is four. In FIG. 4, 211 to 244 are pseudo synapse coupling converters,
201 to 204 are addition nonlinear converters that combine the adder 2a and the nonlinear converter 2b described in FIG. 4, the illustration is omitted because the drawing is complicated as in FIG. 3, but the input lines for receiving the correction signal from the correction means are pseudo synapse coupling converters 211 to 244 and an addition nonlinear converter 20.
It is connected to 1-204. The pseudo synapse coupling converters 211 to 244 also serve as coupling weight coefficients. Regarding the operation of this signal converting means, the operation of the neural elements 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 converting 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.
Upon receiving (X), the process waits until M error signals δ _i (X) are input from the error calculating means or the signal converting means in the subsequent stage. The error signal δ _i (X) is input and the correction amount is ΔW _ij = δ _i (X) · S _iout (X) · (1−S _iout (X)) · S _jin (X) (i = 1 to N , J = 1 to M) (formula 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 corrected by the correction means. 32Z
Sent to.

[0018]

[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). According to the procedure described above, the correction means 32Z calculates the correction amount ΔW (Z) of the conversion parameter of the signal conversion means 31Z, calculates the error signal to be sent to the correction means 32Y based on (Equation 6), and corrects it. The 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 converting means 31Z uses the correction signal ΔW (Z).
Modify internal parameters based on. The error signal δ (Y) is given by (Equation 6).

[0020]

[Equation 2]

[0021] 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 performs environmental data (initial temperature in the heating chamber, commercial power supply voltage level, type of cooking product, initial temperature of cooking product, etc.) when cooking and physical quantity data ( Weight) and temperature of the food (surface,
By learning the relationship with the (center, back surface) data, it is possible to express in a natural way the control method that is not easy to describe with simple rules. In this embodiment, the temperature estimation means 12 is configured by incorporating the information thus obtained. Specifically, the temperature estimating means 12 is configured by using only the signal converting means 31X, 31Y, 31Z of the multilayer perceptron after sufficiently learning 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 is a thing. FIG. 7A shows a change in the cooking-material-specific physical quantity detection means 6 (ambient temperature in the heating chamber), and FIG.
Is the surface temperature of the food, FIG. 7 (c) is the center temperature of the food,
FIG.7 (d) has shown the change of the back surface temperature of a cooked material. The temperature of the cooked food is measured with a thermocouple or the like. Figure 8
Indicates that the initial temperature of the heating chamber 2 is high and the commercial power supply voltage is 100
V, the kind of food is one horse mackerel, the initial temperature of the food is about 1
It shows the characteristics when cooked at 0 ° C.
FIG. 9 shows that the initial temperature of the heating chamber 2 is low and the commercial power supply voltage 10
0V, the type of cooked food is four horse mackerels, and the initial temperature of the cooked food is about 10 ° C., which shows the characteristics when cooking. FIG. 10 shows the characteristics when cooking is performed when the initial temperature of the heating chamber 2 is high, the commercial power supply voltage is 100 V, the type of food is four horse mackerels, and the initial temperature of the food is approximately 10 ° C. is there.

FIGS. 8 (a) to 8 (d), 9 (a) to 9 (d), and 10 (a) to 10 (d) are shown in FIG. 7 (a).
~ Corresponds to Fig. 7 (d). It can be seen that the output voltage change (change in the weight of the cooked product) of the cooked product specific physical quantity detection means 6 varies depending on the initial temperature in the heating chamber and the amount of the cooked product. Similarly, when the power supply voltage is changed, the output changes differently even when the type of food is changed. Such an experiment was similarly carried out for all combinations of the actual cooking environments. Then, the experimental data was input to the neural network model means for learning. That is, to the neural network model means, the weight information of the cooked food physical quantity means 6, the weight information one minute before the present time as the weight change information, the commercial power supply voltage level information of the voltage level detection means 7, Three pieces of information, namely, elapsed time information from the time the power is turned on, which is obtained from the time counting means 8, five pieces of category information, which is obtained from the category selection key 10, and surface information, center temperature information, and rear surface temperature information of the cooked food as an ideal output. Is input and learned, and signal conversion means 31X in the neural network model means,
31Y and 31Z are established, and they are incorporated in the temperature estimation means 12 as a neural network schematic means.

Next, the operation will be described based on the block diagram shown in FIG. First, put the food in the heating chamber,
A cooking category is selected with the category selection key 10 of the operation means 9. Then, cooking is started by the cooking start key 11. The category information is input to the temperature estimation means 12 via the control means 5. The control means 5 outputs a signal to start timing to the timing means 8 and also outputs a heating start signal to heat the heating supply means 3. The timing information of the timing means 8 is input to the temperature estimation means 12. The output of the cooking product specific physical quantity detection means 6 is converted into digital data by the A / D conversion means 14, and the specific physical information (weight information) peculiar to the cooking product is input to the temperature estimation means 12 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 15 and input to the temperature estimation means 12. Temperature estimating means 12
Calculates the surface temperature, the center temperature, and the back surface temperature of the cooked product based on these input signals and information, and outputs the information to the control means 5. The control means 5 operates so as to control the heating supply means 3 based on this estimated temperature information.

Further, although the control means 5, the clock means 8 and the temperature estimation means 12 are all constructed by a 4-pit microcomputer, it is of course possible to construct them by one microcomputer. The temperature estimation means 1
Reference numeral 2 indicates weight change information (two pieces of information at the present time and one minute before) of the cooking product specific physical quantity detection means 6 and the voltage level detection means 7
Five pieces of information, namely, the voltage level information of the commercial power supply voltage obtained, the information on the elapsed time after the power is turned on, which is obtained from the timing means 8, and the category information of the cooking product obtained from the category selection key 10, are inputted. The limitation is not a limitation of the present invention. Further, although the weight information of the cooking product is used as the information of the physical quantity peculiar to the cooking product, it goes without saying that it is also applicable to the color information of the burned eyes, the change information of the shape of the cooking product, and the like. It is also possible to combine a plurality of these pieces of information. Further, although an electric roaster is used as a cooking utensil in this embodiment, it can be applied to a microwave oven and a gas oven.

As described above, according to the present embodiment, the temperature estimation incorporating the neural network model means having a plurality of fixed coupling weight coefficients of the neural network already learned in the environment of the heating chamber where the cooking is actually performed Since it is configured with means,
The finished state of the cooked food can be detected by the surface temperature, the central temperature, and the backside temperature, and the cooked state can be improved more than ever before, which is most suitable for automatic cooking.

[0028]

As is apparent from the above embodiments, according to the present invention, there is provided a heating chamber for storing food to be cooked,
A heating supply means for heating the cooked food, a cooked food unique physical quantity detection means for detecting the unique physical quantity of the cooked food, and a temperature estimation means for estimating the temperature of the cooked food based on the output of the cooked food unique physical quantity detection means. And the control means for controlling the heating and supplying means based on the output of the temperature estimating means, the actual temperature of the cooked food can be indirectly detected in order to recognize the finished state of the cooked food. Therefore,
It is possible to improve the finished state of cooking as compared with the conventional method in which the optimum cooking time is determined from the gradient of the atmospheric temperature and the like.

Further, the temperature estimating means is the surface temperature of the food,
At least one of the center temperature and the back surface temperature is estimated, so that the entire finished state of the cooked food from the front surface to the inside can be known.

Further, the temperature estimation means is a fixed neural network for estimating the temperature (front surface, 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 schematic means having a plurality of coupling weight coefficients of, or has a hierarchical neural network schematic means constructed by combining layers composed of a plurality of neural elements in multiple layers, The temperature of the cooked food can be estimated regardless of the initial temperature in the heating chamber, the initial temperature of the cooked food, the amount of the cooked food, etc., and automatic cooking is possible.

[Brief description of drawings]

FIG. 1 is a configuration block diagram of a cookware according to an embodiment of the present invention.

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

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

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

FIG. 5 is a block diagram of a signal processing unit that employs an error backpropagation method as a learning algorithm used for the cooking utensil.

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

7A to 7D are diagrams showing an example of experimental data of the cooking utensil.

8A to 8D are views showing another example of the experimental data of the cooking utensil.

9A to 9D are diagrams showing another example of experimental data of the cooking utensil.

FIG. 10 (a) to (d) are views showing another example of experimental data of the cooking utensil.

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

FIG. 12 (a) and (b) are views showing an example of experimental data of a conventional cooking utensil.

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

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Cooking utensil 2 Heating chamber 3 Heating supply means 5 Control means 6 Cooking material specific physical quantity detection means 12 Temperature estimation means

Claims (4)

[Claims] 1. A heating chamber for storing a food for cooking, a heating supply means for heating the food, and a food unique physical quantity detecting means for detecting a unique physical quantity of the food.
A cooking utensil comprising a temperature estimating means for estimating the temperature of the cooked food based on the output of the cooking physical quantity detecting means, and a control means for controlling the heating supply means based on the output of the temperature estimating means. 2. The cooking utensil according to claim 1, further comprising a temperature estimating means for estimating at least one of a surface temperature, a central temperature and a back surface temperature of the cooked food. 3. The temperature estimating means internally includes a plurality of coupling weight coefficients of a fixed neural network for estimating a temperature of a food obtained by a method simulating a neural network composed of a plurality of neural elements. 2. The cooking utensil according to claim 1, further comprising a neural network schematic means possessed by. 4. The cooking utensil according to claim 1, wherein the temperature estimating means includes a hierarchical neural network schematic means constructed by combining a plurality of layers composed of a plurality of neural elements in a multilayered manner. ..