An electric rice cooker cooking optimization method and system based on intelligent algorithm

Abstract

The application belongs to the field of intelligent algorithm and dynamic identification technology, and provides an electric rice cooker cooking optimization method and system based on intelligent algorithm, specifically: arranging and calibrating an infrared sensor, then using the sensor to collect data of the electric rice cooker and calculate the mean value, then performing time sequence oil film conversion on the collected mean value data to form an oil film accumulation binary tuple, performing grease accumulation analysis on the oil film accumulation binary tuple and obtaining a pressure control strategy value, and finally performing cooking pressure correction according to the pressure control strategy value; thereby effectively monitoring the grease accumulation condition and real-time operating pressure in the high-pressure electric rice cooker, effectively quantifying the malignant influence of pressure fluctuation caused by such grease accumulation on cooking quality and equipment safety, not only providing dynamic judgment for the intelligent control and long-term operation scheme of the electric rice cooker, but also providing innovative data support for the development of intelligent household appliance technology.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of intelligent algorithm and dynamic identification, and particularly relates to an electric rice cooker cooking optimization method and system based on intelligent algorithm. BACKGROUND

[0002] In order to further improve the demand for efficient cooking and food texture optimization, electric rice cooker technology is constantly improving, among which high-pressure electric rice cookers are particularly representative. High-pressure electric rice cookers rely on their internal heating devices to heat the food and water in the pot, forming a high-temperature and high-pressure sealed environment, thereby achieving fast and efficient cooking effects and optimizing the texture of food. The existing public number CN102090840B discloses a high-pressure electric rice cooker and a rice cooking method. The patent arranges a pressure sensor array inside the electric rice cooker to collect pressure data in real time. By comprehensively processing and analyzing the collected pressure data, it can be determined whether the set threshold is reached or abnormal conditions occur. Based on the data analysis results, the system can dynamically adjust the applied pressure to ensure that the pressure remains within the preset stable range, thereby achieving precise pressure control. Like the above method, many high-pressure electric rice cooker cooking technologies currently use pressure sensors to adjust cooking parameters to optimize cooking quality and ensure equipment safety. However, in the actual process of cooking oily food in a high-pressure electric rice cooker, such methods often lead to a vicious risk of cooking quality and safety due to the accumulation of oil, especially in high-frequency use scenarios in commercial kitchens. When cooking oily food with a high-pressure electric rice cooker, the oil and volatile compounds in the food are transported to the surface of the pressure sensor through convection airflow and steam diffusion. Therefore, there is an urgent need for an electric rice cooker cooking optimization method based on intelligent algorithm to calculate the impact of oil accumulation on sensor performance, thereby improving cooking quality and ensuring the safe operation of the electric rice cooker. SUMMARY

[0003] The purpose of the present application is to provide an electric rice cooker cooking optimization method and system based on intelligent algorithm to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, an electric rice cooker cooking optimization method based on intelligent algorithm is provided, which comprises the following steps:

[0005] S100, arranging and calibrating infrared sensors;

[0006] S200, using sensors to collect data from the electric rice cooker and calculate the mean value;

[0007] S300, time-series oil film transformation of the collected mean value data to form an oil film accumulation binary tuple;

[0008] S400, grease accumulation analysis is performed on the oil film accumulation binary array, and a pressure control strategy value is obtained;

[0009] S500, the cooking pressure is corrected according to the pressure control strategy value.

[0010] Further, in step S100, the method of arranging and calibrating the infrared sensor is:

[0011] The electric rice cooker includes an infrared sensor and a pressure sensor, the infrared sensor is an infrared reflective sensor; the infrared sensor is installed in the central region of the inner cavity of the electric rice cooker or any region parallel to the surface of the pressure sensor, and the installation angle is calibrated to be orthogonal to the central section of the surface of the pressure sensor.

[0012] The infrared reflective sensor can accurately monitor the accumulation of grease by emitting infrared light and measuring the reflected light intensity on the grease film layer, and can provide high-resolution data to effectively reflect the changes in the grease film layer, thereby realizing real-time optimization of the cooking process of the electric rice cooker.

[0013] Further, in step S200, the method of using the sensor to collect data and calculate the average value of the electric rice cooker is: setting the monitoring time interval as k0, k0∈[0.5, 5] seconds, and presetting the infrared monitoring fault tolerance time IMT, IMT∈[5, 10) minutes; when the electric rice cooker is in the running state, the pressure sensor is used to collect the real-time pressure value Pac every k0; when the electric rice cooker changes from the running state to the standby or holding state, the average value of all real-time pressure values is obtained as the pressure level, and the infrared monitoring is started for IMT minutes: every k0 seconds, the infrared sensor emits infrared light and receives the infrared light beam reflected by the surface of the pressure sensor, records the incident light intensity and the corresponding reflected light intensity, and calculates the average value of the incident light intensity and the reflected light intensity within the infrared monitoring fault tolerance time.

[0014] Further, in step S300, the method of time-series oil film transformation on the collected average value data to form the oil film accumulation binary group is: substituting the average value of the incident light intensity and the average value of the reflected light intensity into the reflected light intensity change formula to calculate the grease film layer thickness OFT; the two-dimensional array composed of the pressure level collected under the running state of the electric rice cooker and the corresponding grease film layer thickness is recorded as the oil film accumulation binary group.

[0015] The reflected light intensity change formula is: IrM=I0M×R(OFT); wherein IrM is the average reflected light intensity, I0M is the average incident light intensity, R(OFT) is the reflectivity function, and OFT is the grease film layer thickness. The infrared reflective sensor directly reflects the accumulation of the grease layer by monitoring the change of the reflected light intensity. As the grease film layer thickens, the reflectivity R(OFT) increases, resulting in an increase in the reflected light intensity, and the sensor accurately quantifies the thickness of the grease film layer by measuring the change.

[0016] Further, in step S400, the method of grease accumulation analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is: set a time period as the monitoring period TPh, TPh∈[0.5, 3] hours, collect the average pressure value and the average oil film thickness at equal intervals in the monitoring period, set the reference collection number SID, SID∈(30, 50) times;

[0017] The time scale of obtaining the average pressure value and the average oil film thickness is recorded as the reference point;

[0018] For the monitoring period, the average pressure value of each reference point constitutes a first pressure mapping set, and the average pressure value of each reference point is smoothed using Gaussian filtering, and the processed data constitutes a second pressure mapping set;

[0019] The purpose of processing the average pressure value of each reference point using Gaussian filtering is to reduce random noise in the measurement data, and at the same time reduce noise and better preserve important features of the average pressure value; the standard deviation of each average pressure value is set as the standard deviation of Gaussian filtering;

[0020] Calculate the absolute residual error between the first pressure mapping set and the second pressure mapping set, and if the absolute residual error of any reference point is greater than or equal to the upper quartile of all absolute residual errors, the reference point is recorded as a fluctuation reference point;

[0021] The principle of obtaining the fluctuation reference point is to process the average pressure value data through Gaussian filtering, and then determine the difference between the original data and the filtered data, wherein the absolute residual error is compared with the upper quartile, and the reference point greater than or equal to the upper quartile is recorded as the fluctuation reference point; through the comparison with the upper quartile, the reference point that is still significant even after smoothing can be effectively obtained, and the upper quartile can provide a dynamic threshold setting method, which makes the method more adaptable and flexible to different data sets.

[0022] The time period between any fluctuation reference point and the first non-continuous fluctuation reference point in the reverse time direction is recorded as a sub-fluctuation domain;

[0023] Wherein, the continuously occurring fluctuation reference points refer to a plurality of fluctuation reference points that are continuous in time sequence with the search starting bit fluctuation reference point, so each continuous fluctuation reference point belongs to the sub-fluctuation domain formed by the fluctuation reference point closest in time to the current time;

[0024] The binary pair of the average of the pressure value in each reference point and the average of the oil film thickness is denoted as a strategy measurement pair, the ratio of the average of the oil film thickness to the average of the pressure value is denoted as a film pressure amount Mltg, the reference point corresponding to the maximum value of the film pressure amount in each sub-wave domain is obtained and denoted as a sub-wave singularity point, the average of the Euclidean distance of the sub-wave singularity point and all reference points in the corresponding sub-wave domain is calculated and denoted as a wave core measurement Cmov, and a pressure control strategy value PCSV of the oil film cumulative binary pair is obtained according to each sub-wave domain:

[0025] ;

[0026] Wherein, i1 is an accumulation variable, Cmov avg is the average of the wave core measurements of all sub-wave domains, e is a natural constant, len(Imv i1 ) is the number of reference points in the corresponding sub-wave domain of the i1th reference point, MAX(Mltg i1 ) and MIN(Mltg i1 ) are the maximum value and the minimum value of the film pressure amount in the corresponding sub-wave domain of the i1th reference point.

[0027] Since the calculation of the pressure control strategy value is processed by each sub-wave domain, the risk of increasing equipment overheating or even explosion caused by the delay of timely sensing the overpressure state and reducing the delay of safety measures can be effectively quantified, but the dependence of the division of the sub-wave domain on the average of the pressure value is too large, which leads to the problem that the sub-wave domain analysis process is excessively sensitive and cannot be effectively divided, especially in the period when the absolute residual change fluctuation between the first pressure mapping set and the second pressure mapping set is large and the wave reference points are relatively dense. The existing technology cannot effectively compensate for this excessive sensitivity. In order to eliminate this influence, a more preferred scheme is proposed as follows:

[0028] Further, in step S400, the method for performing grease accumulation analysis on the oil film cumulative binary array and obtaining the pressure control strategy value is: setting a time period as a monitoring period TPh, TPh∈[0.5, 3] hours, and collecting the average of the pressure value and the average of the oil film thickness at equal intervals within the monitoring period, and setting a reference collection number SID, SID∈(30, 50) times;

[0029] The time scale for obtaining the average of the pressure value and the average of the oil film thickness is denoted as an observation time;

[0030] The standard deviation of each oil film thickness average in the oil film cumulative binary array is calculated and denoted as a thickness dispersion degree;

[0031] If the average oil film thickness at any observation time is greater than that at the previous observation time, and the absolute value of the difference is greater than the thickness dispersion, then the observation time is defined as a thickness jump point, otherwise it is a thickness drop point;

[0032] A jump binary tuple is formed with any thickness jump point and its corresponding average oil film thickness, and a smooth curve is obtained by using the splrep and splev functions to perform cubic spline interpolation on the set of jump binary tuples. The value of each time on the smooth curve obtained by fitting is the fitting value. The difference between the fitting value of any thickness drop point and the average oil film thickness is the fitting perception, and the root mean square ratio of the fitting perception that is negative to the fitting perception that is positive is calculated and recorded as the difference perception factor Dep.

[0033] The average oil film thickness of all observation times is normalized to form a thickness normalization, and the product of the average pressure value of any observation time and the thickness normalization is the pressure-controlled phase value Volg.

[0034] The principle of obtaining the pressure-controlled phase value here is actually to amplify the values in the average pressure value of all observation times that are biased towards the maximum value through the thickness normalization, so as to increase the weight of the data with the average pressure value biased towards the maximum value and reduce the weight of the small value. In the mathematical analysis process, it can be understood as achieving the classification effect based on the bias of the maximum value and the minimum value in the set. This enables it to dynamically and effectively reflect the state of the average pressure value of the observation time of the electric rice cooker cooking optimization system, thereby providing mathematical support for the application of the pressure-controlled phase value in time series analysis to observe the adjustment effect, and thus it can identify the trend and periodicity of behavior over time.

[0035] The first thickness jump point and the thickness drop point obtained by reverse time search at any observation time are taken as the high jump trace point and the low drop trace point of the observation time, respectively.

[0036] The pressure-controlled state value Ltco of the observation time is calculated according to the high jump trace point and the low drop trace point. j1 : Ltco j1 = lg[Volg j1 +1] / Hcns j1 ×lg (Lcns j1 ); where j1 is the serial number of the observation time, lg() is the logarithmic function with base 10; Volg j1 , Hcns j1 and Lcns j1 are the pressure-controlled phase values of the j1th observation time and its corresponding high jump trace point and low drop trace point, respectively.

[0037] Take any observation time as the current observation time; record the average value of the pressure value corresponding to an observation time, the average value of the oil film thickness, and the pressure control phase value to form a pressure control phase vector; if the current observation time is a thickness jump point or a thickness drop point, the method for obtaining the pressure control state value of the current observation time is: search from the current observation time in the reverse time direction one by one, calculate the cosine similarity of the pressure control phase vectors corresponding to the observation time and the current observation time, obtain the observation time corresponding to the maximum cosine similarity, and the pressure control state value of the observation time is the pressure control state value of the current observation time, wherein the observation time of the traversal cannot be a thickness jump point or a thickness drop point;

[0038] According to the thickness jump point and the thickness drop point, the pressure control strategy value PCSV of the oil film cumulative binary tuple is calculated:

[0039] ;

[0040] Where j1 is the serial number of the observation time, Ltco j1 is the pressure control state value corresponding to the j1th observation time, avg{} is the average value function, exp() is the exponential function with e as the base, sigmoid is the activation function, and rk() is the ranking coefficient function. The return value obtained by the ranking coefficient function rk(j1) is: obtain the percentile value of all pressure control state values in the TPh period of the j1th observation time.

[0041] Beneficial effects: Under the influence of high temperature and high pressure environment, oil will partially evaporate and change into gas phase. The oil vapor is carried to various areas inside the electric rice cooker, including the surface of the pressure sensor, under the driving of gas and steam. The fatty acids and other volatile compounds in the oil will undergo oxidation or polymerization reaction at high temperature, and will have physical adsorption with solid particles in the steam, gradually depositing on the surface of the pressure sensor, and then forming an adhesive film layer.

[0042] The gradual accumulation of the film layer will cause the surface of the pressure sensor to be covered with a large amount of non-conductive or semi-conductive pollutants, thereby causing the signal drift, sensitivity attenuation and response lag of the sensor, and then causing the internal system to be unable to obtain the real pressure state in the pot in real time, thereby incorrectly adjusting the cooking pressure, causing pressure fluctuation.

[0043] Pressure fluctuation directly affects the uniform heating of food materials, resulting in poor cooking effect, and cannot timely sense the overpressure state, causing delay of safety measures, and thus increasing the risk of overheating and even explosion of the equipment. The accumulation of oil greatly reduces the measurement accuracy of the pressure sensor and causes pressure fluctuation, which has a vicious effect on cooking quality and equipment safety. In commercial kitchens, such safety problems are common, which poses a risk to production personnel.

[0044] Since the pressure control strategy value is divided and calculated according to the abnormal points in the time series of the oil film cumulative binary array, the pressure fluctuation caused by the oil accumulation can be effectively quantified, and the pressure control strategy is obtained through an intelligent algorithm to adjust the cooking pressure and the oil accumulation feedback, thereby realizing the optimization of the cooking effect and the stable guarantee of the equipment safety.

[0045] Further, in step S500, the method for cooking pressure correction according to the pressure control strategy value is: obtaining the pressure control strategy value PCSV; setting the minimum safe pressure; setting the mapping function of the pressure adjustment amount as ΔP = α * (PCSV - M_PCSV), wherein M_PCSV is the median of the pressure control strategy value in the historical data, and α is an adjustment coefficient; if |ΔP| > 0.5 kPa, adjusting the PID parameters through a fuzzy control algorithm; adjusting the pressure to the sum of ΔP and the current real-time pressure value Pac, denoted as the control pressure value P CV , and executing the optimized electric rice cooker cooking pressure: setting the pressure of the cooking process as P CV ;

[0046] Further, the oil accumulation model is set as the oil accumulation amount , wherein β is a model adjustment parameter, and the value is between 0 and 1; the safety threshold is set as OA, and the value is 12-18, and the default value is 15; if OA exceeds the safety threshold, the pressure is reduced to the minimum safe pressure and the alarm system is started.

[0047] The adjustment coefficient α is used to control the constant of the pressure adjustment amount, and a higher α will result in a larger pressure change, and vice versa. In the fuzzy control algorithm, the dynamic adjustment of the PID parameters includes the following steps: establishing a fuzzy rule base, monitoring the pressure state of the system in real time, mapping ΔP and its change rate to the fuzzy set, and calculating the membership degree; through the fuzzy inference engine, the adjustment of the PID parameters is derived according to the preset fuzzy rules; the defuzzification centroid method is used to convert the fuzzy output into specific PID parameter update values; the model parameter β is used to assist in evaluating the oil accumulation amount, and the default setting is the heat transfer efficiency of the oil, which can be dynamically adjusted.

[0048] Preferably, in the present application, all undefined variables can be manually set thresholds if not specifically defined.

[0049] The application further provides an intelligent algorithm-based electric rice cooker cooking optimization system, which comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the intelligent algorithm-based electric rice cooker cooking optimization method when executing the computer program, and the intelligent algorithm-based electric rice cooker cooking optimization system can run in a desktop computer, a notebook computer, a palm computer and a cloud data center, and the executable system can comprise, but is not limited to, a processor, a memory and a server cluster, and the processor executes the computer program to run in the following units:

[0050] A sensor configuration unit is arranged to calibrate the infrared sensor.

[0051] A collection processing unit is arranged to collect data of the electric rice cooker by using the sensor and to calculate the mean value.

[0052] A data calculation and structuring unit is arranged to perform time-series oil film conversion on the collected mean value data to form an oil film accumulation binary tuple.

[0053] An intelligent algorithm unit is arranged to perform grease accumulation analysis on the oil film accumulation binary tuple and to obtain a pressure control strategy value.

[0054] A regulation and evaluation unit is arranged to correct the cooking pressure according to the pressure control strategy value.

[0055] The application provides an intelligent algorithm-based electric rice cooker cooking optimization method and system, monitors the grease accumulation and the real-time running pressure in the high-pressure electric rice cooker, effectively quantifies the malignant influence of the pressure fluctuation caused by the grease accumulation on the cooking quality and the equipment safety, obtains a pressure control strategy by using an intelligent algorithm to adjust the cooking pressure and the grease accumulation feedback, realizes the optimization of the cooking effect and the stable guarantee of the equipment safety, provides scientific reference for the intelligent control and long-term operation scheme of the electric rice cooker, provides innovative data support for the development of the intelligent household appliance technology, and promotes the intelligent household appliance technology. BRIEF DESCRIPTION OF DRAWINGS

[0056] The above and other features of the application will become more apparent from the following detailed description of the embodiments taken in conjunction with the accompanying drawings, in which like reference characters indicate the same or similar elements throughout the drawings, and in which:

[0057] Figure 1A flow chart of a cooking optimization method of an electric rice cooker based on an intelligent algorithm is shown.

[0058] Figure 2 A structure diagram of a cooking optimization system of an electric rice cooker based on an intelligent algorithm is shown. DETAILED DESCRIPTION

[0059] The concept, specific structure and generated technical effects of the present application will be described clearly and completely in combination with embodiments and drawings to fully understand the purpose, scheme and effects of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0060] As shown in Figure 1 A flow chart of a cooking optimization method of an electric rice cooker based on an intelligent algorithm is shown. The cooking optimization method of an electric rice cooker based on an intelligent algorithm according to the embodiments of the present application will be described below in combination with Figure 1 The method comprises the following steps:

[0061] S100, arranging and calibrating an infrared sensor;

[0062] S200, collecting data of the electric rice cooker using the sensor and calculating the mean value;

[0063] S300, performing time sequence oil film conversion on the collected mean value data to form an oil film accumulation binary tuple;

[0064] S400, performing grease accumulation analysis on the oil film accumulation binary tuple and obtaining a pressure control strategy value;

[0065] S500, performing cooking pressure correction according to the pressure control strategy value.

[0066] Further, in step S100, the method of arranging and calibrating the infrared sensor is:

[0067] The electric rice cooker comprises an infrared sensor and a pressure sensor. The infrared sensor is an infrared reflective sensor. The infrared sensor is installed in the central region of the inner cavity of the electric rice cooker or any region parallel to the surface of the pressure sensor, and the installation angle thereof is calibrated to be orthogonal to the central tangent plane of the surface of the pressure sensor.

[0068] The infrared reflective sensor can accurately monitor the accumulation of grease by emitting infrared light and measuring the reflected light intensity on the grease film layer, and can provide high-resolution data to effectively reflect the changes of the grease film layer, thereby realizing real-time optimization of the cooking process of the electric rice cooker.

[0069] Further, in step S200, the method of using sensors to collect data and calculate the average value of the rice cooker is: set the monitoring time interval as k0, k0∈[0.5, 5] seconds, and preset the infrared monitoring fault tolerance time IMT, IMT∈[5, 10) minutes; when the rice cooker is in the running state, collect the real-time pressure value Pac every k0 using the pressure sensor; when the rice cooker changes from the running state to the standby or heat preservation state, obtain the average value of all real-time pressure values as the pressure level, and start the infrared monitoring for IMT minutes: every k0 seconds, use the infrared sensor to emit infrared light and receive the infrared light beam reflected by the surface of the pressure sensor, record the incident light intensity and the corresponding reflected light intensity, and calculate the average value of the incident light intensity and the average value of the reflected light intensity within the infrared monitoring fault tolerance time.

[0070] Further, in step S300, the method of time-series oil film conversion of the collected average value data to form the oil film cumulative binary tuple is: the incident light intensity average value and the reflected light intensity average value are substituted into the reflected light intensity change formula to calculate the oil film layer thickness OFT; the two-dimensional array composed of the pressure level collected under the running state of the rice cooker and the corresponding oil film layer thickness is recorded as the oil film cumulative binary tuple.

[0071] The reflected light intensity change formula is: IrM=I0M×R(OFT); wherein IrM is the average value of the reflected light intensity, I0M is the average value of the incident light intensity, R(OFT) is the reflectivity function, and OFT is the oil film layer thickness. The infrared reflective sensor directly reflects the oil film layer accumulation by monitoring the change of the reflected light intensity. With the thickening of the oil film layer, the reflectivity R(OFT) increases, resulting in the increase of the reflected light intensity. The sensor accurately quantifies the thickness of the oil film layer by measuring the change.

[0072] Further, in step S400, the method of analyzing the oil film cumulative binary array for oil accumulation and obtaining the pressure control strategy value is: set a time period as the monitoring period TPh, TPh∈[0.5, 3] hours, and collect the pressure value average and the oil film thickness average at equal intervals within the monitoring period; set the reference collection number SID, SID∈(30, 50) times;

[0073] The time scale of obtaining the pressure value average and the oil film thickness average is recorded as the reference point;

[0074] For the monitoring period, the pressure value average of each reference point constitutes a first pressure mapping set, and the pressure value average of each reference point is smoothed using Gaussian filtering, and the processed data constitutes a second pressure mapping set;

[0075] The purpose of using Gaussian filtering to process the mean pressure values ​​at each reference point is to reduce random noise in the measurement data, and to better preserve the important characteristics of the mean pressure values ​​while reducing noise; the standard deviation of each mean pressure value is set as the standard deviation of the Gaussian filter.

[0076] Calculate the absolute residual between the first pressure mapping set and the second pressure mapping set. If the absolute residual of any reference point is greater than or equal to the upper quartile of all absolute residuals, then the reference point is recorded as the fluctuation reference point.

[0077] The time interval between any fluctuation reference point and the first discontinuous fluctuation reference point in the reverse time direction is denoted as the sub-fluctuation domain.

[0078] The binary pairs formed by the average pressure value and the average oil film thickness at each reference point are denoted as strategy metric pairs. The ratio of the average oil film thickness to the average pressure value is denoted as the film pressure Mltg. The reference point corresponding to the strategy metric pair with the maximum film pressure in each sub-wave domain is obtained and denoted as the sub-wave singular point. The average Euclidean distance between the sub-wave singular point and all reference points in its corresponding sub-wave domain is calculated and denoted as the wave core metric Cmov. The pressure control strategy value PCSV of the oil film accumulation binary pair is calculated based on each sub-wave domain.

[0079] ;

[0080] Where i1 is the accumulator variable, Cmov avg To obtain the average value of the core metric for all sub-wave domains, where e is the natural constant, len(Imv i1 ) represents the number of reference points in the sub-wave domain corresponding to the i1th reference point, MAX(Mltg i1 ) and MIN(Mltg i1 ) represents the maximum and minimum values ​​of membrane pressure in the sub-wave domain corresponding to the i1th reference point.

[0081] Further, in step S400, the method for performing oil accumulation analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is as follows: set a time period as the monitoring period TPh, TPh∈[0.5,3] hours, collect the average pressure value and the average oil film thickness at equal intervals during the monitoring period, and set the reference collection number SID, SID∈(30,50) times;

[0082] The time scale at which the average pressure value and the average oil film thickness are obtained is recorded as the observation time.

[0083] Calculate the standard deviation of the mean thickness of each oil film in the cumulative oil film binary and record it as the thickness dispersion.

[0084] If the average oil film thickness at any observation time is greater than that at the previous observation time, and the absolute value of the difference is greater than the thickness dispersion, then the observation time is defined as a thickness jump point, otherwise it is a thickness drop point;

[0085] A jump pair is formed by any thickness jump point and its corresponding average oil film thickness, and a smooth curve is obtained by using the splrep and splev functions to perform cubic spline interpolation on the set of jump pairs. The value of each time on the smooth curve obtained by fitting is the fitting value. The difference between the fitting value of any thickness drop point and the average oil film thickness is the fitting perception, and the root mean square ratio of the fitting perception that is negative to the fitting perception that is positive is calculated and recorded as the differential perception factor Dep.

[0086] The average oil film thickness at all observation times is normalized to form a thickness normalization, and the product of the average pressure value at any observation time and the thickness normalization is the pressure control phase value Volg.

[0087] The first thickness jump point and the thickness drop point obtained by reverse time search at any observation time are taken as the high jump trace point and the low drop trace point of the observation time, respectively.

[0088] The pressure control state value Ltco of the observation time is calculated according to the high jump trace point and the low drop trace point. j1 : Ltco j1 = lg[Volg j1 +1] / Hcns j1 ×lg (Lcns j1 ); where j1 is the serial number of the observation time, lg() is the logarithm function with base 10; Volg j1 , Hcns j1 and Lcns j1 are the pressure control phase values of the j1th observation time and its corresponding high jump trace point and low drop trace point, respectively.

[0089] Any observation time is taken as the current observation time, and the average pressure value, the average oil film thickness, and the pressure control phase value corresponding to an observation time are taken as the pressure control similar vector. If the current observation time is a thickness jump point or a thickness drop point, the pressure control state value of the current observation time is obtained by: searching in the reverse time direction from the current observation time, calculating the cosine similarity of the pressure control similar vectors corresponding to the observation time and the current observation time, obtaining the observation time corresponding to the maximum cosine similarity, and taking the pressure control state value of the observation time as the pressure control state value of the current observation time, wherein the observation time of the traversal cannot be a thickness jump point or a thickness drop point.

[0090] The pressure control strategy value PCSV of the oil film cumulative pair is calculated according to the thickness jump point and the thickness drop point:

[0091] ;

[0092] wherein j1 is the serial number of the observation time, Ltco j1 is the pressure control state value corresponding to the j1th observation time, avg{} is the average value function, exp() is the exponential function with the base number e, sigmoid is the activation function, rk() is the ranking coefficient function, and the return value obtained by the ranking coefficient function rk(j1) is: obtaining the percentile value of all pressure control state values in the TPh period at the j1th observation time.

[0093] Further, in step S500, the method for correcting the cooking pressure according to the pressure control strategy value is: obtaining the pressure control strategy value PCSV;Setting the minimum safe pressure;Setting the mapping function of the pressure adjustment amount as ΔP=α*(PCSV– M_PCSV), wherein M_PCSV is the median of the pressure control strategy value in the historical data, and α is the adjustment coefficient;If |ΔP|> 0.5 kPa, adjust the PID parameters through the fuzzy control algorithm;Adjust the pressure to the sum of ΔP and the current real-time pressure value Pac, denoted as the control pressure value P CV , set the pressure to P CV ; Set the oil accumulation model as the oil accumulation amount , wherein β is a model adjustment parameter, and the value is between 0 and 1;Set the safety threshold as OA, the value is 12-18, and the default value is 15;If OA exceeds the safety threshold, reduce the pressure to the minimum safe pressure and start the alarm system.

[0094] The embodiment of the application provides an electric rice cooker cooking optimization system based on an intelligent algorithm, as shown in Figure 2 The embodiment of the application provides an electric rice cooker cooking optimization system based on an intelligent algorithm, as shown in

[0095] The system comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to run in the following system units:

[0096] The sensor configuration unit is configured to arrange and calibrate the infrared sensor.

[0097] The acquisition and processing unit is configured to use the sensor to acquire data and calculate the mean value of the electric rice cooker.

[0098] a data calculation and structuring unit for time-series oil film transformation of the collected mean value data to form an oil film accumulation binary tuple;

[0099] an intelligent algorithm unit for oil grease accumulation analysis of the oil film accumulation binary tuple and obtaining a pressure control strategy value;

[0100] a control evaluation unit for cooking pressure correction according to the pressure control strategy value.

[0101] The intelligent algorithm-based electric rice cooker cooking optimization system can run in a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The system can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the example is only an example of the intelligent algorithm-based electric rice cooker cooking optimization system, and does not constitute a limitation on the intelligent algorithm-based electric rice cooker cooking optimization system, and can include more or less components, or combine certain components, or different components, for example, the intelligent algorithm-based electric rice cooker cooking optimization system can also include an input / output device, a network access device, a bus and the like.

[0102] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like. The processor is a control center of the system, and connects each part of the system through various interfaces and lines.

[0103] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the intelligent algorithm-based rice cooker cooking optimization system by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), and the like. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0104] Although the description of the present application has been quite detailed and particularly described with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present application. Furthermore, the present application is described above in embodiments that the inventors can foresee, and the purpose is to provide a useful description, and non-essential modifications to the present application that have not yet been foreseen can still represent equivalent modifications of the present application.

Claims

1. A smart algorithm based rice cooker cooking optimization method, characterized in that, The method comprises the following steps: S100, arranging and calibrating the infrared sensor; S200, using the sensor to collect data of the electric rice cooker and calculate the mean value; S300, time-series oil film conversion is performed on the collected mean value data to form an oil film cumulative binary tuple; S400, grease accumulation analysis is performed on the oil film cumulative binary tuple to obtain a pressure control strategy value; S500, cooking pressure correction is performed according to the pressure control strategy value; In step S400, the method for performing grease accumulation analysis on the oil film cumulative binary tuple to obtain the pressure control strategy value is as follows: a time period is set as a monitoring time period TPh, TPh∈[0.5, 3] hours, the mean value of the pressure value and the mean value of the oil film thickness are collected at equal intervals within the monitoring time period, a reference collection number SID is set, SID∈(30, 50) times; The time scale at which the mean value of the pressure value and the mean value of the oil film thickness are obtained is recorded as a reference point; the mean value of the pressure value at each reference point in the monitoring time period constitutes a first pressure mapping set, the mean value of the pressure value at each reference point is smoothed by using Gaussian filtering, and the processed data constitute a second pressure mapping set; The absolute residual error between the first pressure mapping set and the second pressure mapping set is calculated, if the absolute residual error of any reference point is greater than or equal to the upper quartile of all absolute residual errors, the reference point is recorded as a fluctuation reference point, and the time period between any fluctuation reference point and the first non-continuous fluctuation reference point in the reverse time direction thereof is recorded as a sub-fluctuation domain; The binary tuple constituted by the mean value of the pressure value and the mean value of the oil film thickness in each reference point is recorded as a strategy measurement pair, the ratio of the mean value of the oil film thickness to the mean value of the pressure value is recorded as a film pressure amount Mltg, the reference point corresponding to the maximum value of the film pressure amount in each sub-fluctuation domain is recorded as a sub-fluctuation singular point, the average value of the Euclidean distance of all reference points in the sub-fluctuation domain corresponding to the sub-fluctuation singular point is calculated and recorded as a fluctuation core measurement Cmov, and the pressure control strategy value of the oil film cumulative binary tuple is calculated according to each sub-fluctuation domain.

2. The intelligent algorithm-based cooking optimization method of an electric rice cooker according to claim 1, characterized in that, In step S100, the method for arranging and calibrating the infrared sensor is as follows: the electric rice cooker comprises an infrared sensor and a pressure sensor, the infrared sensor is an infrared reflective sensor; the infrared sensor is installed in the central region of the inner cavity of the electric rice cooker or any region parallel to the surface of the pressure sensor, and the installation angle thereof is calibrated to be orthogonal to the central tangent plane of the surface of the pressure sensor.

3. The intelligent algorithm-based cooking optimization method of an electric rice cooker according to claim 1, characterized in that, In step S200, the method for using the sensor to collect data of the electric rice cooker and calculate the mean value is as follows: the monitoring time interval is set as k0, k0∈[0.5, 5] seconds, a preset infrared monitoring fault tolerance time IMT is set, IMT∈[5, 10) minutes; when the electric rice cooker is in a running state, the real-time pressure value Pac is collected by using the pressure sensor every k0; when the electric rice cooker changes from the running state to the standby or heat preservation state, the average value of all real-time pressure values is obtained as the pressure level, and the infrared monitoring is started for IMT minutes: every k0 seconds, the infrared sensor is used to emit infrared light and receive the infrared light beam reflected by the surface of the pressure sensor, the incident light intensity and the corresponding reflected light intensity are recorded, and the mean value of the incident light intensity and the mean value of the reflected light intensity within the infrared monitoring fault tolerance time are calculated.

4. The intelligent algorithm-based cooking optimization method of an electric rice cooker according to claim 1, characterized in that, In step S300, the method of time sequence oil film transformation for the collected mean value data is: the incident light intensity mean value and the reflected light intensity mean value are substituted into the reflected light intensity change formula to calculate the oil film layer thickness OFT; the two-dimensional array composed of the collected pressure level and the corresponding oil film layer thickness in the electric rice cooker running state is recorded as the oil film cumulative binary tuple.

5. The intelligent algorithm based cooking optimization method of an electric rice cooker according to claim 1, characterized in that, In step S400, the method of oil accumulation analysis on the oil film cumulative binary array and the pressure control strategy value obtained can be replaced as follows: a time period is set as a monitoring period TPh, TPh∈[0.5, 3] hours, the pressure value mean and the oil film thickness mean are collected at equal intervals in the monitoring period, a reference collection number SID is set, SID∈(30, 50) times; The time scale of obtaining the pressure value mean and the oil film thickness mean is recorded as the observation time; the standard deviation of each oil film thickness mean in the oil film cumulative binary tuple is calculated and recorded as the thickness dispersion; in the monitoring period, if the oil film thickness mean of any observation time is greater than that of the previous observation time, and the absolute value of the difference is greater than the thickness dispersion, then the observation time is defined as a thickness jump point, otherwise it is a thickness drop point; The jump binary tuple is composed of any thickness jump point and its corresponding oil film thickness mean, a smooth curve is obtained by using the splrep and splev functions to perform cubic spline interpolation on the set constructed by the jump binary tuple, and the value of each time on the smooth curve obtained by fitting is the fitting value; the difference between the fitting value of any thickness drop point and the oil film thickness mean is the fitting perception, and the root mean square ratio of the fitting perception which is negative to the fitting perception which is positive is calculated and recorded as the difference perception factor Dep; The oil film thickness mean of all observation times is normalized to form the thickness normalization, and the product of the pressure value mean and the thickness normalization of any observation time is the pressure control phase value Volg; the first thickness jump point and the thickness drop point obtained by inverse time search at any observation time are taken as the high jump trace point and the low drop trace point of the observation time, respectively. The pressure-controlled eigenvalue Ltco at the observation time is calculated based on the high jump and low drop points. j1 Ltco j1 =lg[Volg j1 +1] / Hcns j1 ×lg (Lcns j1 ); where j1 is the sequence number of the observation time, and lg() is the logarithmic function to the base 10; Volg j1 Hcns j1 and Lcns j1 These are the pressure control phase values ​​for the j1st observation time and its corresponding high jump and low drop points, respectively; Any observation time is taken as the current observation time; the pressure value mean, the oil film thickness mean and the pressure control phase value corresponding to the observation time are recorded as the pressure control similar vector; if the current observation time is a thickness jump point or a thickness drop point, the method of obtaining the pressure control state value of the current observation time is: the observation times are searched one by one in the reverse time direction from the current observation time, the cosine similarity of the pressure control similar vectors corresponding to the observation times and the current observation time is calculated, the observation time corresponding to the maximum cosine similarity is obtained, and the pressure control state value of the observation time is taken as the pressure control state value of the current observation time, wherein the observation times in the traversal cannot be thickness jump points or thickness drop points; the pressure control strategy value of the oil film cumulative binary tuple is calculated according to the thickness jump points and the thickness drop points.

6. The intelligent algorithm-based electric rice cooker cooking optimization method according to claim 1, characterized in that, In step S500, the method for cooking pressure correction according to the pressure control strategy value is: obtaining the pressure control strategy value PCSV; setting the minimum safe pressure; setting the mapping function of the pressure adjustment amount as ΔP = α * (PCSV - M_PCSV), wherein M_PCSV is the median of the pressure control strategy values in the historical data, and α is an adjustment coefficient; if |ΔP| > 0.5 kPa, adjusting the PID parameters through a fuzzy control algorithm; The pressure is adjusted to the sum of ΔP and the current real-time pressure value Pac, denoted as the regulated pressure value P CV The pressure is set to P CV .

7. A smart algorithm based rice cooker cooking optimization system, characterized in that, The cooking optimization system based on the intelligent algorithm includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the cooking optimization method based on the intelligent algorithm are implemented. The cooking optimization system based on the intelligent algorithm is used in desktop computers, notebook computers, palm computers, and cloud data center computing devices.

Images