CN120523009A - Intelligent cooking robot data control system and method based on automatic adjustment - Google Patents
Intelligent cooking robot data control system and method based on automatic adjustmentInfo
- Publication number
- CN120523009A CN120523009A CN202510704912.5A CN202510704912A CN120523009A CN 120523009 A CN120523009 A CN 120523009A CN 202510704912 A CN202510704912 A CN 202510704912A CN 120523009 A CN120523009 A CN 120523009A
- Authority
- CN
- China
- Prior art keywords
- cooking
- load
- stage
- data
- equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B11/00—Automatic controllers
- G05B11/01—Automatic controllers electric
- G05B11/36—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential
- G05B11/42—Automatic controllers electric with provision for obtaining particular characteristics, e.g. proportional, integral, differential for obtaining a characteristic which is both proportional and time-dependent, e.g. P. I., P. I. D.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Baking, Grill, Roasting (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an intelligent cooking robot data control system and method based on automatic adjustment, and relates to the technical field of intelligent cooking robot data control, wherein the method comprises the following steps of acquiring cooking related data and order information, and dividing a cooking model of cooking equipment; dividing the cooking stages of dishes, recording corresponding rotating speed and heating power parameters, defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index through constructing a neural network architecture, calculating target load and load deviation of rotating equipment of each cooking stage based on the relation model of the target load and the food weight, executing an adjustment strategy according to the calculated load deviation, namely, when the load deviation is less than or equal to 0, improving the rotating speed of the rotating equipment and the heating power of the cooking equipment, shortening the remaining time of the current stage, and when the load deviation is greater than 0, reducing the rotating speed, and recalculating the remaining time of the adjusted current stage.
Description
Technical Field
The invention relates to the technical field of intelligent cooking robot data control, in particular to an intelligent cooking robot data control system and method based on automatic adjustment.
Background
Along with the rapid development of intelligent cooking technology, when the traditional cooking robot faces diversified food material characteristics, complex cooking technology and dynamic load changes, the problems of stiff control strategy and insufficient real-time adaptability are gradually exposed, and the high requirements of modern catering industry on cooking efficiency, dish consistency and equipment intelligence are difficult to meet.
However, when the traditional data control method of the cooking robot is used for coping with complex cooking scenes, the traditional data control method of the cooking robot often has the problems that firstly, the traditional system mostly adopts a control mode of fixed rotating speed, heating power and preset time, the traditional system cannot be dynamically adjusted according to real-time changes of weight and state of food, secondly, the traditional scheme depends on manual preset cooking parameters, lacks of real-time monitoring and analysis of the load of rotating equipment, cannot timely trigger an adjustment strategy when abnormal load is caused by food adhesion, caking and the like in the cooking process, causes overload shutdown of the equipment or interruption of a cooking process, and has poor multi-stage process coordination, wherein complex dishes usually comprise a plurality of cooking stages, the load characteristics and process targets of each stage are different, the traditional method is difficult to dynamically optimize time distribution based on real-time load data of each stage, so that process connection unbalance among stages is caused, and the overall cooking effect is affected.
Disclosure of Invention
The invention aims to provide an intelligent cooking robot data control system and method based on automatic adjustment, so as to solve the problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme that the intelligent cooking robot data control method based on automatic adjustment comprises the following steps:
Acquiring cooking related data and order information, and dividing a cooking model of cooking equipment;
Dividing the cooking stages of dishes, recording corresponding rotation speed and heating power parameters, and defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index through constructing a neural network architecture;
Calculating target load and load deviation of the rotating equipment in each cooking stage based on the relation model of the target load and the weight of the food;
And executing an adjustment strategy according to the calculated load deviation, namely increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment when the load deviation is smaller than or equal to 0, shortening the residual time of the current stage, and reducing the rotating speed by adopting a PID control algorithm when the load deviation is larger than 0, and recalculating the residual time of the current stage after adjustment.
The cooking related data and order information are acquired, and the cooking model of the cooking equipment is divided, and the specific steps comprise:
Obtaining food material data, cooking environment data, cooking equipment data, cooking process data and order requirement information, wherein the food material data comprises the type and weight of food materials, the cooking environment data comprises the temperature, the humidity and the oil smoke concentration during cooking, the cooking equipment data comprises the type, the power, the heating mode, the state of an actuator (whether heating and stirring are running) and the running state (whether cooking and idle), and the cooking process data comprises the cooking mode, the cooking time range, the fire requirement, the operation steps, the flavoring throwing sequence and the throwing amount;
Judging whether the weight of the food is in a safety range [ Wmin, wmax ], prompting a user of insufficient food when w < Wmin ], suspending starting, entering a normal cooking process when w epsilon [ Wmin, wmax ], and triggering an overweight treatment mode when w > Wmax, wherein w represents the weight of the obtained food, wmin represents the lower limit of a set safety weight range, is defined as a times of a preset standard weight, a represents a safety lower limit adjustment coefficient, the value is smaller than 1, wmax represents the upper limit of the set safety weight range, b times of the preset standard weight, b represents a safety upper limit adjustment coefficient, and the value is larger than 1.
Dividing the cooking stages of dishes, recording corresponding rotation speed and heating power parameters, carrying out normalization processing and feature learning on food weight and target load torque data of each stage by constructing a neural network architecture integrating a full-connection layer and a convolution layer, and defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index, wherein the specific steps comprise:
Dividing the dish cooking stages into n cooking stages { S1, S2, & gt, sn }, recording the rotation speed parameters { z1, z2, & gt, zn } of the rotating equipment and the heating power parameters { p1, p2, & gt, pn }, respectively, wherein S1, S2, & gt, sn represents the 1 st, 2, & gt, n cooking stages, n represents the total number of cooking stages dividing the dish cooking stages, z1, z2, & gt, zn represents the 1 st, 2, & gt, the target rotation speed of the rotating equipment corresponding to the n cooking stages, p1, p2, & gt, pn represents the heating power setting values of the cooking equipment corresponding to the 1 st, 2, & gt, n cooking stages;
Defining a relation model of target load and food weight for each cooking stage by constructing a neural network architecture, wherein the target load takes torque as a measurement index, and the specific process is that collected food weight data of each cooking stage and target load torque data measured by a torque sensor at a corresponding stage are processed by adopting a normalized preprocessing coding mode, the coded data are input into a constructed neural network model integrating a full-connection layer and a convolution layer, and the relation model of the target load and the food weight of each cooking stage is output by learning and mapping a correlation mode among input data features.
Calculating the target load and load deviation of the rotating equipment in each cooking stage based on the relation model of the target load and the food weight, wherein the specific steps comprise:
calculating the target load of each cooking stage rotating device based on the relation model of the target load and the weight of the food material, and further calculating the load deviation of each cooking stage rotating device, wherein a calculation formula is shown as delta L i=Li,actual-Li,target;
Where Δl i represents a load deviation corresponding to the i-th cooking stage, L i,actual represents an i-th cooking stage rotating apparatus actual load, and L i,target represents an i-th cooking stage rotating apparatus target load.
Executing an adjustment strategy according to the calculated load deviation, namely when the load deviation is smaller than or equal to 0, increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment, shortening the residual time of the current stage, and when the load deviation is larger than 0, reducing the rotating speed by adopting a PID control algorithm, and recalculating the residual time of the adjusted current stage, wherein the specific steps comprise:
Executing an adjustment strategy according to the calculated load deviation, and when DeltaL i is less than or equal to 0, increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment, and recalculating the residual time of the current stage, wherein t i'=max(ti*(1-β*|ΔLi|),tmin ' is defined, t i ' represents the residual time period from the moment of detecting the load deviation to the adjustment of the preset ending time of the ith cooking stage, t i represents the initial value of the residual time of the preset total time of the ith stage when the load deviation is detected, beta represents a shortening coefficient, t min represents a minimum residual time threshold value, and when DeltaL i >0, adopting a PID control algorithm to reduce the rotating speed and recalculating the residual time t i'=ti*(1+α*ΔLi), wherein alpha represents a delay constant, t i ' represents the residual time period from the moment of detecting the load deviation to the adjustment of the preset ending time of the ith cooking stage, and t i represents the initial value of the residual time of the preset total time of the ith stage when the load deviation is detected.
The system comprises a data acquisition module, a cooking stage modeling module, a load calculation and deviation analysis module and an adjustment execution module, wherein the data acquisition module is used for acquiring cooking related data and order information, the cooking stage modeling module is used for dividing a cooking model of cooking equipment, dividing cooking stages of dishes and recording corresponding rotating speed and heating power parameters, a neural network architecture is constructed to define a relation model of target load and food weight of each cooking stage taking torque as a measurement index, the load calculation and deviation analysis module is used for calculating target load and load deviation of rotating equipment of each cooking stage based on the relation model of target load and food weight, the adjustment execution module is used for executing an adjustment strategy according to the calculated load deviation, when the load deviation is smaller than or equal to 0, increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment, shortening the residual time of the current stage, and when the load deviation is larger than 0, reducing the rotating speed by adopting a PID control algorithm, and recalculating the residual time of the adjusted current stage.
The data acquisition module comprises a data acquisition unit and a data verification and safety processing unit, wherein the data acquisition unit is used for acquiring food material data, cooking environment data, cooking equipment data, cooking process data and order demand information, the data verification and safety processing unit is used for judging whether the weight of the food material is in a safety range [ Wmin, wmax ], wherein Wmin represents the lower limit of a preset standard food material weight, a represents a safety lower limit adjustment coefficient, the value is smaller than 1, wmax represents the upper limit of the preset safety weight range, b represents a safety upper limit adjustment coefficient, and the value is larger than 1.
The cooking phase modeling module comprises a phase division and parameter recording unit and a neural network modeling unit, wherein the phase division and parameter recording unit is used for dividing a dish cooking phase into n cooking phases { S1, S2, & gt, sn }, respectively recording rotating speed parameters { z1, z2, & gt, zn } of a rotating device corresponding to each phase and heating power parameters { p1, p2, & gt, pn }, wherein S1, S2, & gt, sn represents the 1,2, n cooking phases, n represents the total number of the cooking phases for dividing the dish cooking phase, z1, z2, & gt, zn represents the 1,2, & gt, the target rotating speed of the rotating device corresponding to the n cooking phases, p1, p2, & gt, pn represents heating power set values of the cooking device corresponding to the 1,2, & gt, and the neural network modeling unit is used for defining a target load and food weight relation model for each cooking phase by constructing a neural network architecture.
The load calculation and deviation analysis module comprises a target load calculation unit and a load deviation calculation unit, wherein the target load calculation unit is used for calculating the target load of each cooking stage rotating device based on a relation model of the target load and the weight of the food materials, and the load deviation calculation unit is used for calculating the load deviation of each cooking stage rotating device.
The adjustment execution module comprises an equipment parameter adjustment unit and a remaining time calculation unit, wherein the equipment parameter adjustment unit is used for adjusting the rotating equipment rotating speed and the heating power according to the load deviation, and the remaining time calculation unit is used for recalculating the remaining time of the current stage according to the load deviation and the equipment parameter adjustment.
Compared with the prior art, the invention has the beneficial effects that:
1. by constructing a relation model of target load and food weight of each cooking stage and combining the real-time collected load data of the rotary equipment, calculating load deviation and dynamically adjusting cooking parameters, unlike the cooking modes with fixed parameters in the prior art, the invention captures the dynamic change in the cooking process and realizes self-adaptive cooking control;
2. The invention introduces a rotating speed regulation and residual time dynamic calculation mechanism based on a PID control algorithm, combines the real-time load deviation and the running state of the equipment, automatically adjusts the rotating speed of the rotating equipment and the residual time of the current stage, and optimizes the running parameters of the equipment and the time distribution according to the actual load condition in the cooking process, unlike the control mode lacking real-time feedback and intelligent adjustment in the prior art.
Drawings
FIG. 1 is a flow chart of an intelligent cooking robot data control method based on automatic adjustment according to the present invention;
Fig. 2 is a schematic structural diagram of the intelligent cooking robot data control system based on automatic adjustment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In an embodiment, as shown in fig. 1-2, the invention provides a technical scheme, an intelligent cooking robot data control method based on automatic adjustment, which comprises the following steps:
Acquiring cooking related data and order information, and dividing a cooking model of cooking equipment;
Dividing the cooking stages of dishes, recording corresponding rotation speed and heating power parameters, and defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index through constructing a neural network architecture;
Calculating target load and load deviation of the rotating equipment in each cooking stage based on the relation model of the target load and the weight of the food;
And executing an adjustment strategy according to the calculated load deviation, namely increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment when the load deviation is smaller than or equal to 0, shortening the residual time of the current stage, and reducing the rotating speed by adopting a PID control algorithm when the load deviation is larger than 0, and recalculating the residual time of the current stage after adjustment.
The cooking related data and order information are acquired, and the cooking model of the cooking equipment is divided, and the specific steps comprise:
Obtaining food material data, cooking environment data, cooking equipment data, cooking process data and order requirement information, wherein the food material data comprises the type and weight of food materials, the cooking environment data comprises the temperature, the humidity and the oil smoke concentration during cooking, the cooking equipment data comprises the type, the power, the heating mode, the state of an actuator (whether heating and stirring are running) and the running state (whether cooking and idle), and the cooking process data comprises the cooking mode, the cooking time range, the fire requirement, the operation steps, the flavoring throwing sequence and the throwing amount;
Judging whether the weight of the food is in a safety range [ Wmin, wmax ], prompting a user of insufficient food when w < Wmin ], suspending starting, entering a normal cooking process when w epsilon [ Wmin, wmax ], and triggering an overweight treatment mode when w > Wmax, wherein w represents the weight of the obtained food, wmin represents the lower limit of a set safety weight range, is defined as a times of a preset standard weight, a represents a safety lower limit adjustment coefficient, the value is smaller than 1, wmax represents the upper limit of the set safety weight range, b times of the preset standard weight, b represents a safety upper limit adjustment coefficient, and the value is larger than 1.
Further, the tomato fried eggs are manufactured through the cooking robot, according to the tomato fried egg recipe, 3 standard food materials (about 150 g) are used for eggs, 2 standard food materials (about 300 g) are used for tomatoes, and the cooking stage is divided into 3 stages, namely egg stirring, egg frying, stir-frying and tomato stewed products;
Weighing 160g (over standard 10 g) of eggs and 280g (lower than standard 20 g) of tomatoes;
the maximum rotating speed of the rotating equipment (stirring paddle) is 500rpm, and the maximum power of the heating equipment is 2000W;
stirring egg at stirring speed of 300rpm and heating power of 0W for 2 min;
the stir-frying stage of stir-frying eggs, namely the stir-frying rotating speed is 200rpm, the heating power is 1500W, and the preset time is 3 minutes;
the braising stage of tomatoes comprises the steps of stirring at a speed of 150rpm, heating at a power of 1200W and presetting for 5 minutes;
The safe weight range is as follows:
450g (150 g+300 g) of the total weight;
Wmin=0.9*450=405g,Wmax=1.1*450=495g;
The current total weight is 160+280=440 (e 405,495), and the normal cooking process is entered.
Dividing the cooking stages of dishes, recording corresponding rotation speed and heating power parameters, carrying out normalization processing and feature learning on food weight and target load torque data of each stage by constructing a neural network architecture integrating a full-connection layer and a convolution layer, and defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index, wherein the specific steps comprise:
Dividing the dish cooking stages into n cooking stages { S1, S2, & gt, sn }, recording the rotation speed parameters { z1, z2, & gt, zn } of the rotating equipment and the heating power parameters { p1, p2, & gt, pn }, respectively, wherein S1, S2, & gt, sn represents the 1 st, 2, & gt, n cooking stages, n represents the total number of cooking stages dividing the dish cooking stages, z1, z2, & gt, zn represents the 1 st, 2, & gt, the target rotation speed of the rotating equipment corresponding to the n cooking stages, p1, p2, & gt, pn represents the heating power setting values of the cooking equipment corresponding to the 1 st, 2, & gt, n cooking stages;
Defining a relation model of target load and food weight for each cooking stage by constructing a neural network architecture, wherein the target load takes torque as a measurement index, and the specific process is that collected food weight data of each cooking stage and target load torque data measured by a torque sensor at a corresponding stage are processed by adopting a normalized preprocessing coding mode, the coded data are input into a constructed neural network model integrating a full-connection layer and a convolution layer, and the relation model of the target load and the food weight of each cooking stage is output by learning and mapping a correlation mode among input data features.
Calculating the target load and load deviation of the rotating equipment in each cooking stage based on the relation model of the target load and the food weight, wherein the specific steps comprise:
calculating the target load of each cooking stage rotating device based on the relation model of the target load and the weight of the food material, and further calculating the load deviation of each cooking stage rotating device, wherein a calculation formula is shown as delta L i=Li,actual-Li,target;
Where Δl i represents a load deviation corresponding to the i-th cooking stage, L i,actual represents an i-th cooking stage rotating apparatus actual load, and L i,target represents an i-th cooking stage rotating apparatus target load.
Further, in the egg stirring stage, when the weight of eggs is 150g, the target load torque is 5N.m, 160g of the current egg weight is input, and the neural network outputs the target load L 1,target =5.3N.m in the egg stirring stage;
The egg stir-frying stage comprises the steps of inputting 160g of current egg weight and 280g of tomato data, and outputting a target load L 2,target =8.2N.m in the egg stir-frying stage by a neural network;
stage of braising tomato:
Inputting the condition of the residual food materials, and outputting a target load L 3,target =6.5N.m by the neural network;
After stirring for 1 minute, a torque sensor detects that L 1,actual=4.8N.m;ΔL1 = -0.5N.m, and the current stage is insufficient in load;
After stirring for 2 minutes, a torque sensor detects L 2,actual=9N.m;ΔL2 =0.8N.m, and the load at the current stage is judged to be out of standard;
after stirring for 3 minutes, the torque sensor measures L 3,actual=6.8N.m;ΔL1 =0.3N.m, and the load at the current stage is judged to be out of standard.
Executing an adjustment strategy according to the calculated load deviation, namely when the load deviation is smaller than or equal to 0, increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment, shortening the residual time of the current stage, and when the load deviation is larger than 0, reducing the rotating speed by adopting a PID control algorithm, and recalculating the residual time of the adjusted current stage, wherein the specific steps comprise:
Executing an adjustment strategy according to the calculated load deviation, and when DeltaL i is less than or equal to 0, increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment, and recalculating the residual time of the current stage, wherein t i'=max(ti*(1-β*|ΔLi|),tmin ' is defined, t i ' represents the residual time period from the moment of detecting the load deviation to the adjustment of the preset ending time of the ith cooking stage, t i represents the initial value of the residual time of the preset total time of the ith stage when the load deviation is detected, beta represents a shortening coefficient, t min represents a minimum residual time threshold value, and when DeltaL i >0, adopting a PID control algorithm to reduce the rotating speed and recalculating the residual time t i'=ti*(1+α*ΔLi), wherein alpha represents a delay constant, t i ' represents the residual time period from the moment of detecting the load deviation to the adjustment of the preset ending time of the ith cooking stage, and t i represents the initial value of the residual time of the preset total time of the ith stage when the load deviation is detected.
Further, in the egg stirring stage, the stirring rotation speed is increased to 330rpm, and the residual time is calculated by the initial residual time t 1 =1 min, the shortening coefficient beta=0.2N.m -1 and the minimum threshold t min =0.5 min, and t 1' =0.9;
The egg stir-frying stage comprises the steps of reducing the rotating speed through a PID algorithm, and calculating the residual time, wherein the initial residual time t 2 =1 minute, and the delay coefficient alpha=0.5 N.m -1,t2' =1.4;
The tomato stewed process comprises the steps of reducing the rotating speed through a PID algorithm, and calculating the residual time, wherein the initial residual time t 3 =2 minutes, and the delay coefficient alpha=0.5 N.m -1,t3' =2.3.
The system comprises a data acquisition module, a cooking stage modeling module, a load calculation and deviation analysis module and an adjustment execution module, wherein the data acquisition module is used for acquiring cooking related data and order information, the cooking stage modeling module is used for dividing a cooking model of cooking equipment, dividing the cooking stage of dishes and recording corresponding rotating speed and heating power parameters, a neural network architecture is constructed to define a relation model of target load and food weight of each cooking stage taking torque as a measurement index, the load calculation and deviation analysis module is used for calculating target load and load deviation of rotating equipment of each cooking stage based on the relation model of target load and food weight, the adjustment execution module is used for executing an adjustment strategy according to the calculated load deviation, when the load deviation is smaller than or equal to 0, the rotating speed of the rotating equipment and the heating power of the cooking equipment are improved, the remaining time of the current stage is shortened, when the load deviation is larger than 0, the rotating speed is reduced by adopting a PID control algorithm, and the remaining time of the current stage after adjustment is recalculated.
The data acquisition module comprises a data acquisition unit and a data verification and safety processing unit, wherein the data acquisition unit is used for acquiring food material data, cooking environment data, cooking equipment data, cooking process data and order demand information, the data verification and safety processing unit is used for judging whether the weight of the food material is in a safety range [ Wmin, wmax ], wherein Wmin represents the lower limit of a preset standard food material weight, a represents a safety lower limit adjustment coefficient, the value is smaller than 1, wmax represents the upper limit of the preset safety weight range, b represents b times of the preset standard food material weight, and b represents a safety upper limit adjustment coefficient, and the value is larger than 1.
The cooking stage modeling module comprises a stage division and parameter recording unit and a neural network modeling unit, wherein the stage division and parameter recording unit is used for dividing the cooking stage of the dishes into n cooking stages { S1, S2,..Sn }, the rotational speed parameters { z1, z2, }, zn } of the rotating equipment corresponding to each stage and the heating power parameters { p1, p2, }, pn }, wherein S1, S2, & gt, sn represents the 1,2, & gt, n cooking stages, n represents the total number of the cooking stages dividing the cooking stage of the dishes, z1, z2, & gt, zn represents the 1,2, & gt, the target rotational speed of the rotating equipment corresponding to the n cooking stages, p1, p2, & gt, pn represents the heating power set value of the cooking equipment corresponding to the n cooking stages, and the neural network modeling unit is used for defining a model of the relation between the target load and the weight of the food for each cooking stage by constructing a neural network architecture.
The load calculation and deviation analysis module comprises a target load calculation unit and a load deviation calculation unit, wherein the target load calculation unit is used for calculating the target load of each cooking stage rotating device based on a relation model of the target load and the weight of the food materials, and the load deviation calculation unit is used for calculating the load deviation of each cooking stage rotating device.
The adjustment execution module comprises an equipment parameter adjustment unit and a residual time calculation unit, wherein the equipment parameter adjustment unit is used for adjusting the rotating equipment rotating speed and the heating power according to the load deviation, and the residual time calculation unit is used for recalculating the residual time of the current stage according to the load deviation and the equipment parameter adjustment.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. The intelligent cooking robot data control method based on automatic adjustment is characterized by comprising the following steps of:
Acquiring cooking related data and order information, and dividing a cooking model of cooking equipment;
Dividing the cooking stages of dishes, recording corresponding rotation speed and heating power parameters, and defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index through constructing a neural network architecture;
Calculating target load and load deviation of the rotating equipment in each cooking stage based on the relation model of the target load and the weight of the food;
And executing an adjustment strategy according to the calculated load deviation, namely increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment when the load deviation is smaller than or equal to 0, shortening the residual time of the current stage, and reducing the rotating speed by adopting a PID control algorithm when the load deviation is larger than 0, and recalculating the residual time of the current stage after adjustment.
2. The method for controlling data of an intelligent cooking robot based on automatic adjustment of claim 1, wherein the steps of obtaining cooking related data and order information, and performing cooking model division of cooking equipment comprise:
Food material data, cooking environment data, cooking equipment data, cooking process data and order demand information are acquired, wherein the food material data comprise the type and weight of food materials, the cooking environment data comprise the temperature, the humidity and the oil smoke concentration during cooking, the cooking equipment data comprise the type, the power, the heating mode, the actuator state and the running state of equipment, and the cooking process data comprise the cooking mode, the cooking time range, the fire requirements, the operation steps, the flavoring throwing sequence and the throwing amount;
Judging whether the weight of the food is in a safety range [ Wmin, wmax ], prompting a user of insufficient food when w < Wmin ], suspending starting, entering a normal cooking process when w epsilon [ Wmin, wmax ], and triggering an overweight treatment mode when w > Wmax, wherein w represents the weight of the obtained food, wmin represents the lower limit of a set safety weight range, is defined as a times of a preset standard weight, a represents a safety lower limit adjustment coefficient, the value is smaller than 1, wmax represents the upper limit of the set safety weight range, b times of the preset standard weight, b represents a safety upper limit adjustment coefficient, and the value is larger than 1.
3. The method for controlling the intelligent cooking robot data based on automatic adjustment according to claim 2, wherein the steps of dividing the cooking stages of the dishes and recording the corresponding rotation speed and heating power parameters, carrying out normalization processing and feature learning on the food weight and target load torque data of each stage by constructing a neural network architecture integrating a full-connection layer and a convolution layer, and defining a relation model of target load and food weight of each cooking stage by taking torque as a measurement index comprise the following specific steps:
Dividing the dish cooking stages into n cooking stages { S1, S2, & gt, sn }, recording the rotation speed parameters { z1, z2, & gt, zn } of the rotating equipment and the heating power parameters { p1, p2, & gt, pn }, respectively, wherein S1, S2, & gt, sn represents the 1 st, 2, & gt, n cooking stages, n represents the total number of cooking stages dividing the dish cooking stages, z1, z2, & gt, zn represents the 1 st, 2, & gt, the target rotation speed of the rotating equipment corresponding to the n cooking stages, p1, p2, & gt, pn represents the heating power setting values of the cooking equipment corresponding to the 1 st, 2, & gt, n cooking stages;
Defining a relation model of target load and food weight for each cooking stage by constructing a neural network architecture, wherein the target load takes torque as a measurement index, and the specific process is that collected food weight data of each cooking stage and target load torque data measured by a torque sensor at a corresponding stage are processed by adopting a normalized preprocessing coding mode, the coded data are input into a constructed neural network model integrating a full-connection layer and a convolution layer, and the relation model of the target load and the food weight of each cooking stage is output by learning and mapping a correlation mode among input data features.
4. The method for controlling data of an intelligent cooking robot based on automatic adjustment according to claim 3, wherein the calculating of the target load and the load deviation of the rotating device in each cooking stage based on the relation model of the target load and the weight of the food comprises the following steps:
calculating the target load of each cooking stage rotating device based on the relation model of the target load and the weight of the food material, and further calculating the load deviation of each cooking stage rotating device, wherein a calculation formula is shown as delta L i=Li,actual-Li,target;
Where Δl i represents a load deviation corresponding to the i-th cooking stage, L i,actual represents an i-th cooking stage rotating apparatus actual load, and L i,target represents an i-th cooking stage rotating apparatus target load.
5. The method for controlling data of an intelligent cooking robot based on automatic adjustment according to claim 4, wherein the adjusting strategy is executed according to the calculated load deviation, when the load deviation is less than or equal to 0, the rotating speed of the rotating equipment and the heating power of the cooking equipment are increased, the remaining time of the current stage is shortened, and when the load deviation is greater than 0, the rotating speed is reduced by adopting a PID control algorithm, and the remaining time of the adjusted current stage is recalculated, the method comprises the following specific steps:
Executing an adjustment strategy according to the calculated load deviation, and when DeltaL i is less than or equal to 0, increasing the rotating speed of the rotating equipment and the heating power of the cooking equipment, and recalculating the residual time of the current stage, wherein t i'=max(ti*(1-β*|ΔLi|),tmin ' is defined, t i ' represents the residual time period from the moment of detecting the load deviation to the adjustment of the preset ending time of the ith cooking stage, t i represents the initial value of the residual time of the preset total time of the ith stage when the load deviation is detected, beta represents a shortening coefficient, t min represents a minimum residual time threshold value, and when DeltaL i >0, adopting a PID control algorithm to reduce the rotating speed and recalculating the residual time t i'=ti*(1+α*ΔLi), wherein alpha represents a delay constant, t i ' represents the residual time period from the moment of detecting the load deviation to the adjustment of the preset ending time of the ith cooking stage, and t i represents the initial value of the residual time of the preset total time of the ith stage when the load deviation is detected.
6. The intelligent cooking robot data control system based on automatic adjustment is characterized by comprising a data acquisition module, a cooking stage modeling module, a load calculation and deviation analysis module and an adjustment execution module, wherein the data acquisition module is used for acquiring cooking related data and order information, the cooking stage modeling module is used for dividing a cooking model of cooking equipment, dividing a cooking stage of dishes and recording corresponding rotating speed and heating power parameters, a neural network architecture is constructed, a relation model of target load and food weight of each cooking stage taking torque as a measurement index is defined, the load calculation and deviation analysis module is used for calculating target load and load deviation of each cooking stage rotating equipment based on the relation model of target load and food weight, the adjustment execution module is used for executing an adjustment strategy according to the calculated load deviation, when the load deviation is smaller than or equal to 0, the rotating speed of the rotating equipment and the heating power of the cooking equipment are improved, the remaining time of the current stage is shortened, when the load deviation is larger than 0, the rotating speed is reduced by adopting a PID control algorithm, and the remaining time of the current stage after adjustment is recalculated.
7. The intelligent cooking robot data control system based on automatic adjustment according to claim 6, wherein the data acquisition module comprises a data acquisition unit and a data verification and safety processing unit, the data acquisition unit is used for acquiring food material data, cooking environment data, cooking equipment data, cooking process data and order demand information, the data verification and safety processing unit is used for judging whether the weight of the food material is in a safety range [ Wmin, wmax ], wherein Wmin represents the lower limit of a set safety weight range, a is defined as a times of a preset standard food material weight, a represents a safety lower limit adjustment coefficient, the value is smaller than 1, wmax represents the upper limit of the set safety weight range, b is defined as b times of the preset standard food material weight, and b represents the safety upper limit adjustment coefficient, and the value is larger than 1.
8. The intelligent cooking robot data control system based on automatic adjustment according to claim 7, wherein the cooking phase modeling module includes a phase division and parameter recording unit for dividing a cooking phase of a dish into n cooking phases { S1, S2,..sn }, respectively recording rotational speed parameters { z1, z2, }, zn } of a rotating device corresponding to each phase and heating power parameters { p1, p2,..pn }, of a cooking device, wherein S1, S2,., sn represents 1,2,., n cooking phases, n represents a total number of cooking phases dividing the cooking phase of the dish, z1, z2,., zn represents a target rotational speed of the rotating device corresponding to the n cooking phases, p1, p2,., pn represents a set value of the heating power of the device corresponding to the n cooking phases, and the neural network modeling unit is used for defining a weight-to-load model for each of the neural network by means of the neural network.
9. The intelligent cooking robot data control system based on automatic adjustment according to claim 8, wherein the load calculation and deviation analysis module comprises a target load calculation unit and a load deviation calculation unit, wherein the target load calculation unit is used for calculating a target load of each cooking stage rotating device based on a relation model of the target load and the weight of food materials, and the load deviation calculation unit is used for calculating a load deviation of each cooking stage rotating device.
10. The intelligent cooking robot data control system based on automatic adjustment according to claim 9, wherein the adjustment execution module comprises an equipment parameter adjustment unit and a remaining time calculation unit, the equipment parameter adjustment unit is used for adjusting the rotating equipment rotating speed and the heating power according to the load deviation, and the remaining time calculation unit is used for recalculating the remaining time of the current stage according to the load deviation and the equipment parameter adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510704912.5A CN120523009B (en) | 2025-05-29 | 2025-05-29 | Intelligent cooking robot data control system and method based on automatic adjustment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510704912.5A CN120523009B (en) | 2025-05-29 | 2025-05-29 | Intelligent cooking robot data control system and method based on automatic adjustment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120523009A true CN120523009A (en) | 2025-08-22 |
| CN120523009B CN120523009B (en) | 2025-11-04 |
Family
ID=96752915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510704912.5A Active CN120523009B (en) | 2025-05-29 | 2025-05-29 | Intelligent cooking robot data control system and method based on automatic adjustment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120523009B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170221296A1 (en) * | 2016-02-02 | 2017-08-03 | 6d bytes inc. | Automated preparation and dispensation of food and beverage products |
| CN110115489A (en) * | 2018-02-05 | 2019-08-13 | 佛山市顺德区美的电热电器制造有限公司 | The control method and cooking machine of cooking machine |
| CN114027706A (en) * | 2021-10-29 | 2022-02-11 | 添可智能科技有限公司 | Intelligent cooking equipment control method and intelligent cooking equipment |
| CN119376290A (en) * | 2024-12-30 | 2025-01-28 | 宁波舜韵电子有限公司 | Intelligent variable frequency cooking equipment multi-mode control method and system |
| CN119436222A (en) * | 2024-10-31 | 2025-02-14 | 广州嘉润餐饮设备有限公司 | Combined furnace heating control system based on Internet of Things |
| CN119625719A (en) * | 2024-10-16 | 2025-03-14 | 昆明花浅姬科技有限公司 | A food processing control method and system based on AI |
-
2025
- 2025-05-29 CN CN202510704912.5A patent/CN120523009B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170221296A1 (en) * | 2016-02-02 | 2017-08-03 | 6d bytes inc. | Automated preparation and dispensation of food and beverage products |
| CN110115489A (en) * | 2018-02-05 | 2019-08-13 | 佛山市顺德区美的电热电器制造有限公司 | The control method and cooking machine of cooking machine |
| CN114027706A (en) * | 2021-10-29 | 2022-02-11 | 添可智能科技有限公司 | Intelligent cooking equipment control method and intelligent cooking equipment |
| CN119625719A (en) * | 2024-10-16 | 2025-03-14 | 昆明花浅姬科技有限公司 | A food processing control method and system based on AI |
| CN119436222A (en) * | 2024-10-31 | 2025-02-14 | 广州嘉润餐饮设备有限公司 | Combined furnace heating control system based on Internet of Things |
| CN119376290A (en) * | 2024-12-30 | 2025-01-28 | 宁波舜韵电子有限公司 | Intelligent variable frequency cooking equipment multi-mode control method and system |
Non-Patent Citations (1)
| Title |
|---|
| 叶承;何海华;卓宏明;: "自动炒菜机定量加料器的设计", 浙江国际海运职业技术学院学报, no. 02, 15 June 2018 (2018-06-15), pages 69 - 72 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120523009B (en) | 2025-11-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115013861B (en) | Indoor temperature control method and device based on heating system | |
| CN116191572B (en) | An intelligent control method and system for a photovoltaic inverter | |
| CN117905638B (en) | Wind driven generator optimal control method and system based on reinforcement learning | |
| CN108934416A (en) | One kind being based on BP neural network combined harvester multi-parameter operation-control system and method | |
| CN118486386A (en) | Automatic control system for preparation process of amphiphilic polyaminohexadecanol ester with high salt resistance | |
| CN120523009B (en) | Intelligent cooking robot data control system and method based on automatic adjustment | |
| CN107634548B (en) | Intelligent control method for active power change rate of wind power plant | |
| CN120560061A (en) | A method and system for automatically controlling intelligent cooking equipment | |
| EP3880959B1 (en) | Method of cooling a wind turbine | |
| CN118536047B (en) | Intelligent pig behavior abnormality monitoring method and system | |
| CN118980228A (en) | Adaptive parameter control method for fish fillet air-drying production line | |
| CN114321722B (en) | Pressure balancing method, device, storage medium and processor for steam pipeline network | |
| CN117008527B (en) | Processing control method, system and medium for marinated food | |
| CN117968762A (en) | A temperature and humidity sensor and a temperature and humidity monitoring method | |
| CN117829000A (en) | A photovoltaic system control method based on real-time mechanical analysis | |
| CN116711534A (en) | An optimal electric harvester component control method based on grain loss rate and electric harvester | |
| CN115271147A (en) | New energy oscillation prediction and decision-making aid method and system based on machine learning | |
| CN121091771B (en) | A Smart Control Method for Chimney Stacks Based on a Three-Dimensional Shelving Microenvironment Model | |
| EP3942176A1 (en) | Method for determining performance parameters in real time | |
| CN118868423B (en) | Virtual power plant control terminal capable of realizing novel load monitoring function | |
| CN119225166B (en) | A remote control system and method for three-dimensional shrimp and crab breeding facilities | |
| CN119423182B (en) | Methods for monitoring and controlling oxygen content in yellow tea fermentation equipment | |
| CN113729505B (en) | Detection method, device and equipment of cooking equipment and computer readable storage medium | |
| CN121386959A (en) | A smart cooking system and method based on multimodal sensing and adaptive control | |
| CN120428588A (en) | Cooking equipment control method, device, equipment and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |