Electric cooker cooking optimization method and system based on intelligent algorithm

Abstract

The invention belongs to the technical field of intelligent algorithms and dynamic identification, and provides an electric cooker cooking optimization method and system based on an intelligent algorithm, and the method specifically comprises the steps: arranging and calibrating an infrared sensor, carrying out the data collection and mean value calculation of an electric cooker through the sensor, carrying out the time sequence oil film conversion of the collected mean value data, and carrying out the time sequence oil film conversion of the collected mean value data; forming an oil film accumulation two-tuple, performing oil accumulation analysis on the oil film accumulation two-tuple to obtain a pressure control strategy value, and finally performing cooking pressure correction according to the pressure control strategy value; therefore, the grease accumulation condition and the real-time operation pressure in the high-pressure electric cooker are effectively monitored, and the vicious influence of the cooking quality and the equipment safety caused by pressure fluctuation caused by grease accumulation is effectively quantified, so that dynamic judgment is provided for the scheme of intelligent control and long-term operation of the electric cooker; and innovative data support is provided for the development of the intelligent household electrical appliance technology.

Description

Technical Field

[0001] The invention belongs to the field of intelligent algorithms and dynamic recognition technology, and in particular relates to an electric rice cooker cooking optimization method and system based on intelligent algorithms. Background Art

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

[0003] The purpose of the present invention is to propose an electric rice cooker cooking optimization method and system based on an 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 object, according to one aspect of the present invention, a method for optimizing cooking of a rice cooker based on an intelligent algorithm is provided, the method comprising the following steps: S100, arranging and calibrating infrared sensors; S200, using sensors to collect data and calculate mean values ​​of the rice cooker; S300, performing a time series oil film transformation on the collected mean value data to form an oil film accumulation binary group; S400, performing grease backlog analysis on the oil film accumulation binary array and obtaining a pressure control strategy value; S500, performing cooking pressure correction according to the pressure control strategy value.

[0005] Furthermore, in step S100, the method of arranging and calibrating the infrared sensors is: 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 area of ​​the inner cavity of the electric rice cooker or in any area parallel to the surface of the pressure sensor, and its installation angle is calibrated to be orthogonal to the central section of the pressure sensor surface.

[0006] The infrared reflective sensor can accurately monitor the accumulation of grease by emitting infrared light and measuring the intensity of its reflected light on the grease film layer. It also provides high-resolution data that can effectively reflect the changes in the grease film layer, thereby achieving real-time optimization of the rice cooker cooking process.

[0007] Further, in step S200, the method of using the sensor to collect data and calculate the mean of the rice cooker is: setting the monitoring time interval to k0, k0∈[0.5,5] seconds, and presetting the infrared monitoring fault-tolerant time IMT, IMT∈[5,10) minutes; when the rice cooker is in operation, using the pressure sensor to collect the real-time pressure value Pac every k0; when the rice cooker is changed from the operation state to the standby or insulation state, obtaining the average value of all real-time pressure values ​​as the pressure level, and starting infrared monitoring of IMT minutes: every k0 seconds, using the infrared sensor to emit infrared light and receive the infrared light beam reflected by the surface of the pressure sensor, recording the incident light intensity and the corresponding reflected light intensity, and calculating the incident light intensity mean and the reflected light intensity mean within the infrared monitoring fault-tolerant time.

[0008] Further, in step S300, the collected mean data is subjected to a time-series oil film transformation to form an oil film accumulation binary group by substituting the incident light intensity mean and the reflected light intensity mean into the reflected light intensity change formula to calculate the oil film thickness OFT; and recording a two-dimensional array consisting of the pressure level collected under the operation state of the rice cooker and the corresponding oil film thickness as an oil film accumulation binary group.

[0009] The formula for the change in reflected light intensity is: IrM = I0M × R (OFT); where IrM is the mean reflected light intensity, I0M is the mean incident light intensity, R (OFT) is the reflectivity function, and OFT is the thickness of the grease film. The infrared reflective sensor directly reflects the accumulation of the grease layer by monitoring the change in reflected light intensity. As the grease film thickens, the reflectivity R (OFT) increases, resulting in an increase in the reflected light intensity. The sensor measures this change and accurately quantifies the thickness of the grease film.

[0010] Further, in step S400, the method for performing grease backlog analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is: set a time period as a monitoring period TPh, TPh∈[0.5,3] hours, collect the mean value of pressure value and the mean value of oil film thickness at equal intervals within the monitoring period, set the reference collection number SID, SID∈(30,50) times; The time scale for obtaining the mean pressure value and the mean oil film thickness is recorded as a reference point; During the monitoring period, the mean pressure values ​​of each reference point constitute a first pressure mapping set, and the mean pressure values ​​of each reference point are smoothed using Gaussian filtering, and the processed data constitute a second pressure mapping set; The purpose of using Gaussian filtering to process the mean pressure value of each reference point is to reduce the random noise in the measurement data, and to better retain the important characteristics of the mean pressure value while reducing the noise; the standard deviation of the mean pressure value is set as the standard deviation of the Gaussian filter; Calculate the absolute residuals between the first pressure mapping set and the second pressure mapping set, and if the absolute residual of any reference point is greater than or equal to the upper quartile of all absolute residuals, record the reference point as a fluctuation reference point; The principle of obtaining the fluctuation reference point is to process the mean pressure value data through Gaussian filtering, and then determine it by comparing the difference between the original data and the filtered data, wherein the absolute residual 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; by comparing with the upper quartile, a 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.

[0011] The time period between any fluctuation reference point and the first non-continuous fluctuation reference point in the reverse time direction is recorded as the sub-fluctuation domain; The continuously occurring fluctuation reference points refer to a number of fluctuation reference points that are continuous in time sequence with the fluctuation reference point of the search start position, so each continuous fluctuation reference point belongs to a sub-fluctuation domain formed by a fluctuation reference point that is closest to the current moment in time; The two-tuple consisting of the mean pressure value and the mean oil film thickness in each reference point is recorded as a strategy metric pair, and the ratio of the mean oil film thickness to the mean pressure value is recorded as the film pressure Mltg. The reference point of the strategy metric pair corresponding to the maximum value of the film pressure in each sub-fluctuation domain is obtained and recorded as a sub-fluctuation singular point; the average Euclidean distance between the sub-fluctuation singular point and all reference points in the corresponding sub-fluctuation domain is calculated and recorded as the fluctuation core metric Cmov; the pressure control strategy value PCSV of the oil film accumulation two-tuple is calculated according to each sub-fluctuation domain: ; Where i1 is the accumulation variable, Cmov avg To obtain the average value of the core measurement of all sub-fluctuation domains, e is a natural constant, len(Imv i1 ) is the number of reference points in the sub-fluctuation domain corresponding to the i1-th reference point, MAX(Mltg i1 ) and MIN(Mltg i1 ) are the maximum and minimum values ​​of the membrane pressure in the sub-fluctuation domain corresponding to the i1th reference point.

[0012] Since the calculation of the pressure control strategy value is obtained by processing each sub-fluctuation domain, it can effectively quantify the risk of equipment overheating or even explosion caused by the inability to timely perceive the overpressure state and reduce the delay in safety measures. However, the division of the sub-fluctuation domain is too dependent on the mean value of the pressure value, which will lead to the problem of excessive sensitivity and ineffective division in the sub-fluctuation domain analysis process, especially when the absolute residual change between the first pressure mapping set and the second pressure mapping set fluctuates greatly and the fluctuation reference points occur more frequently. This problem is more prominent. However, the existing technology cannot effectively compensate for this oversensitivity phenomenon. In order to eliminate this influence, the present invention proposes a more preferred solution as follows: Further, in step S400, the method for performing grease backlog analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is: set a time period as a monitoring period TPh, TPh∈[0.5,3] hours, collect the mean value of pressure value and the mean value of oil film thickness at equal intervals within the monitoring period, set the reference collection number SID, SID∈(30,50) times; The time scale for obtaining the mean pressure value and the mean oil film thickness is recorded as the observation time; Calculate and obtain the standard deviation of the mean value of each oil film thickness in the oil film accumulation binary group, and record it as thickness dispersion; During the monitoring period, if the oil film thickness at any observation time is greater than the average value 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; The jump binary group is composed of any thickness jump point and its corresponding oil film thickness mean value. The set constructed by the jump binary group is interpolated by cubic spline using splrep and splev functions to obtain a smooth curve. The value on the smooth curve obtained by fitting at each moment is the fitting value; the difference between the fitting value of any thickness drop point and its oil film thickness mean value is the fitting perception degree, and the root mean square ratio of the fitting perception degree of a negative number to the fitting perception degree of a positive number is calculated and recorded as the differential perception factor Dep; The average value of the oil film thickness at all observation times is normalized to form a thickness normalized value. The product of the average pressure value at any observation time and the thickness normalized value is the pressure-controlled phase value Volg. The principle of obtaining the pressure-controlled phase value here is actually to amplify the value that is biased towards the maximum value in the mean pressure value of all observation moments through the thickness normalization, thereby increasing the weighting of the data that is biased towards the maximum value of the mean pressure value and reducing the weight of the smaller value. In the process of mathematical analysis, it can be understood as achieving a classification effect based on the bias of the maximum and minimum values ​​in the set. This enables it to dynamically and effectively reflect the mean pressure value state of the rice cooker cooking optimization system at the observation moment, thereby providing mathematical support for the application of the pressure-controlled phase value in time series analysis to observe the regulation effect, and thus can identify the trend and periodicity of the behavior over time.

[0013] The first thickness jump point and thickness drop point obtained by reverse time search at any observation time are respectively used as the high jump tracing point and low drop tracing point at the observation time; The pressure-controlled state eigenvalue Ltco at the observation time is calculated based on the high jump tracing point and the low drop tracing 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 voltage-controlled phase values ​​of the j1th observation moment and its corresponding high jump tracing point and low drop tracing point respectively; Take any observation time as the current observation time; record the mean pressure value corresponding to an observation time, the mean oil film thickness and the pressure control phase value to form a pressure control similarity vector; if the current observation time is a thickness jump point or a thickness drop point, the method for obtaining the pressure control state eigenvalue of the current observation time is: traverse and search one by one in the reverse time direction from the current observation time, calculate the cosine similarity of the traversed observation time and the pressure control similarity vector corresponding to the current observation time, obtain the observation time corresponding to the maximum cosine similarity, and use the pressure control state eigenvalue of the observation time as the pressure control state eigenvalue of the current observation time, wherein the traversed observation time cannot be a thickness jump point or a thickness drop point; Calculate the pressure control strategy value PCSV of the oil film accumulation binary group according to the thickness jump point and thickness drop point: ; Where j1 is the serial number of the observation time, Ltco j1is the voltage-controlled state eigenvalue corresponding to the j1th observation time, avg{} is the average value function, exp() is the exponential function with the natural constant e as the base, sigmoid is the activation function, rk() is the sorting coefficient function, and the return value obtained by the sorting coefficient function rk(j1) is: Get the percentile value of all voltage-controlled state eigenvalues ​​in the TPh period at the j1th observation time.

[0014] Beneficial effects: Under the influence of high temperature and high pressure environment, the grease will partially evaporate and turn into gas phase. Driven by gas and steam, the grease vapor is carried to various areas inside the rice cooker, including the surface of the pressure sensor. The fatty acids and other volatile compounds in the grease will undergo oxidation or polymerization reaction at high temperature, and physically adsorb with the solid particles in the steam, gradually depositing on the surface of the pressure sensor, and then forming an adhesive film layer.

[0015] 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, which will cause the sensor's signal drift, sensitivity attenuation and response lag, and thus cause the internal system to be unable to obtain the actual pressure state inside the pot in real time, thereby incorrectly adjusting the cooking pressure and causing pressure fluctuations.

[0016] Pressure fluctuations directly affect the uniform heating of ingredients, resulting in poor cooking results, and the inability to detect overpressure in time delays safety measures, which in turn increases the risk of equipment overheating or even explosion. Grease accumulation greatly reduces the measurement accuracy of pressure sensors and causes pressure fluctuations, which in turn has a negative impact on cooking quality and equipment safety. This safety issue is common in commercial kitchens, posing a risk to the safety of production personnel.

[0017] Since the pressure control strategy value is divided and calculated according to the abnormal points in the time series of the binary array of oil film accumulation, it can effectively quantify the adverse effects of pressure fluctuations caused by such oil accumulation on cooking quality and equipment safety. The pressure control strategy is obtained through an intelligent algorithm to adjust the cooking pressure and oil accumulation feedback, thereby optimizing the cooking effect and ensuring the safety of equipment.

[0018] 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 safety pressure; setting the mapping function of the pressure adjustment amount to ΔP=α*(PCSV– M_PCSV), where 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, adjusting the PID parameters through the fuzzy control algorithm; adjusting the pressure to the sum of ΔP and the current real-time pressure value Pac, recorded as the control pressure value P CV , optimize the rice cooker cooking pressure: set the pressure of the cooking process to PCV ; Furthermore, the grease accumulation model is set as the grease accumulation amount , where β is the model adjustment parameter, with a value between 0 and 1; the safety threshold is set to OA value 12-18, with a default value of 15. If OA exceeds the safety threshold, the pressure is reduced to the minimum safety pressure and the alarm system is activated.

[0019] The adjustment coefficient α is used to control the constant of the pressure adjustment amount. A higher α will lead to a greater pressure change, and vice versa. In the fuzzy control algorithm, the dynamic adjustment of PID parameters includes the following steps: establish a fuzzy rule base, monitor the pressure state of the system in real time, map ΔP and its rate of change to the fuzzy set, and calculate its membership; use the fuzzy inference engine to derive the adjustment of PID parameters according to the preset fuzzy rules; use the centroid method to convert the fuzzy output into a specific PID parameter update value; the model parameter β is used to assist in evaluating the amount of grease accumulation, and the default setting is the thermal conductivity efficiency of the grease, which can be adjusted dynamically.

[0020] Preferably, all undefined variables in the present invention, if not clearly defined, can be manually set thresholds.

[0021] The present invention also provides an electric rice cooker cooking optimization system based on an intelligent algorithm, the electric rice cooker cooking optimization system based on an intelligent algorithm comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor, the processor implements the steps in the electric rice cooker cooking optimization method based on the intelligent algorithm when executing the computer program, the electric rice cooker cooking optimization system based on the intelligent algorithm can be run in computing devices such as desktop computers, notebook computers, PDAs, and cloud data centers, and the executable system may include, 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 system units: A sensor configuration unit, used for arranging and calibrating infrared sensors; A collection and processing unit, used for collecting data and calculating mean values ​​of the rice cooker using sensors; The data calculation and structuring unit is used to perform time-series oil film transformation on the collected mean data to form oil film accumulation binary groups; Intelligent algorithm unit, used to analyze the oil film accumulation binary array and obtain the pressure control strategy value; The control and evaluation unit is used to correct the cooking pressure according to the pressure control strategy value.

[0022] The beneficial effects of the present invention are as follows: the present invention provides an electric rice cooker cooking optimization method and system based on an intelligent algorithm, which monitors the grease accumulation and real-time operating pressure in the high-pressure electric rice cooker, thereby effectively quantifying the adverse effects of pressure fluctuations caused by such grease accumulation on cooking quality and equipment safety, and obtaining a pressure control strategy through an intelligent algorithm to adjust the cooking pressure and grease accumulation feedback, thereby achieving optimization of the cooking effect and a stable guarantee of equipment safety, which not only provides a scientific reference for the intelligent control and long-term operation solutions of the electric rice cooker, but also provides innovative data support for the development of smart home appliance technology, thereby promoting the smart home appliance technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings: Figure 1 Shown is a flow chart of an electric rice cooker cooking optimization method based on intelligent algorithm; Figure 2 Shown is a structural diagram of a rice cooker cooking optimization system based on an intelligent algorithm. DETAILED DESCRIPTION

[0024] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0025] like Figure 1 The figure shows a flow chart of a rice cooker cooking optimization method based on intelligent algorithm. Figure 1 A rice cooker cooking optimization method based on an intelligent algorithm according to an embodiment of the present invention is described, and the method comprises the following steps: S100, arranging and calibrating infrared sensors; S200, using sensors to collect data and calculate mean values ​​of the rice cooker; S300, performing a time series oil film transformation on the collected mean value data to form an oil film accumulation binary group; S400, performing grease backlog analysis on the oil film accumulation binary array and obtaining a pressure control strategy value; S500, performing cooking pressure correction according to the pressure control strategy value.

[0026] Furthermore, in step S100, the method of arranging and calibrating the infrared sensors is: 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 area of ​​the inner cavity of the electric rice cooker or in any area parallel to the surface of the pressure sensor, and its installation angle is calibrated to be orthogonal to the central section of the pressure sensor surface.

[0027] The infrared reflective sensor can accurately monitor the accumulation of grease by emitting infrared light and measuring the intensity of its reflected light on the grease film layer. It also provides high-resolution data that can effectively reflect the changes in the grease film layer, thereby achieving real-time optimization of the rice cooker cooking process.

[0028] Further, in step S200, the method of using the sensor to collect data and calculate the mean of the rice cooker is: setting the monitoring time interval to k0, k0∈[0.5,5] seconds, and presetting the infrared monitoring fault-tolerant time IMT, IMT∈[5,10) minutes; when the rice cooker is in operation, using the pressure sensor to collect the real-time pressure value Pac every k0; when the rice cooker is changed from the operation state to the standby or insulation state, obtaining the average value of all real-time pressure values ​​as the pressure level, and starting infrared monitoring of IMT minutes: every k0 seconds, using the infrared sensor to emit infrared light and receive the infrared light beam reflected by the surface of the pressure sensor, recording the incident light intensity and the corresponding reflected light intensity, and calculating the incident light intensity mean and the reflected light intensity mean within the infrared monitoring fault-tolerant time.

[0029] Further, in step S300, the collected mean data is subjected to a time-series oil film transformation to form an oil film accumulation binary group by substituting the incident light intensity mean and the reflected light intensity mean into the reflected light intensity change formula to calculate the oil film thickness OFT; and recording a two-dimensional array consisting of the pressure level collected under the operation state of the rice cooker and the corresponding oil film thickness as an oil film accumulation binary group.

[0030] The formula for the change in reflected light intensity is: IrM = I0M × R (OFT); where IrM is the mean reflected light intensity, I0M is the mean incident light intensity, R (OFT) is the reflectivity function, and OFT is the thickness of the grease film. The infrared reflective sensor directly reflects the accumulation of the grease layer by monitoring the change in reflected light intensity. As the grease film thickens, the reflectivity R (OFT) increases, resulting in an increase in the reflected light intensity. The sensor measures this change and accurately quantifies the thickness of the grease film.

[0031] Further, in step S400, the method for performing grease backlog analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is: set a time period as a monitoring period TPh, TPh∈[0.5,3] hours, collect the mean value of pressure value and the mean value of oil film thickness at equal intervals within the monitoring period, set the reference collection number SID, SID∈(30,50) times; The time scale for obtaining the mean pressure value and the mean oil film thickness is recorded as a reference point; During the monitoring period, the mean pressure values ​​of each reference point constitute a first pressure mapping set, and the mean pressure values ​​of each reference point are smoothed using Gaussian filtering, and the processed data constitute a second pressure mapping set; The purpose of using Gaussian filtering to process the mean pressure value of each reference point is to reduce the random noise in the measurement data, and to better retain the important characteristics of the mean pressure value while reducing the noise; the standard deviation of the mean pressure value is set as the standard deviation of the Gaussian filter; Calculate the absolute residuals between the first pressure mapping set and the second pressure mapping set, and if the absolute residual of any reference point is greater than or equal to the upper quartile of all absolute residuals, record the reference point as a fluctuation reference point; The time period between any fluctuation reference point and the first non-continuous fluctuation reference point in the reverse time direction is recorded as the sub-fluctuation domain; The two-tuple consisting of the mean pressure value and the mean oil film thickness in each reference point is recorded as a strategy metric pair, and the ratio of the mean oil film thickness to the mean pressure value is recorded as the film pressure Mltg. The reference point of the strategy metric pair corresponding to the maximum value of the film pressure in each sub-fluctuation domain is obtained and recorded as a sub-fluctuation singular point; the average Euclidean distance between the sub-fluctuation singular point and all reference points in the corresponding sub-fluctuation domain is calculated and recorded as the fluctuation core metric Cmov; the pressure control strategy value PCSV of the oil film accumulation two-tuple is calculated according to each sub-fluctuation domain: ; Where i1 is the accumulation variable, Cmov avg To obtain the average value of the core measurement of all sub-fluctuation domains, e is a natural constant, len(Imv i1 ) is the number of reference points in the sub-fluctuation domain corresponding to the i1-th reference point, MAX(Mltg i1 ) and MIN(Mltg i1 ) are the maximum and minimum values ​​of the membrane pressure in the sub-fluctuation domain corresponding to the i1th reference point.

[0032] Further, in step S400, the method for performing grease backlog analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is: set a time period as a monitoring period TPh, TPh∈[0.5,3] hours, collect the mean value of pressure value and the mean value of oil film thickness at equal intervals within the monitoring period, set the reference collection number SID, SID∈(30,50) times; The time scale for obtaining the mean pressure value and the mean oil film thickness is recorded as the observation time; Calculate and obtain the standard deviation of the mean value of each oil film thickness in the oil film accumulation binary group, and record it as thickness dispersion; During the monitoring period, if the oil film thickness at any observation time is greater than the average value 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; The jump binary group is composed of any thickness jump point and its corresponding oil film thickness mean value. The set constructed by the jump binary group is interpolated by cubic spline using splrep and splev functions to obtain a smooth curve. The value on the smooth curve obtained by fitting at each moment is the fitting value; the difference between the fitting value of any thickness drop point and its oil film thickness mean value is the fitting perception degree, and the root mean square ratio of the fitting perception degree of a negative number to the fitting perception degree of a positive number is calculated and recorded as the differential perception factor Dep; The average value of the oil film thickness at all observation times is normalized to form a thickness normalized value. The product of the average pressure value at any observation time and the thickness normalized value is the pressure-controlled phase value Volg. The first thickness jump point and thickness drop point obtained by reverse time search at any observation time are respectively used as the high jump tracing point and low drop tracing point at the observation time; The pressure-controlled state eigenvalue Ltco at the observation time is calculated based on the high jump tracing point and the low drop tracing 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 voltage-controlled phase values ​​of the j1th observation moment and its corresponding high jump tracing point and low drop tracing point respectively; Take any observation time as the current observation time; record the mean pressure value corresponding to an observation time, the mean oil film thickness and the pressure control phase value to form a pressure control similarity vector; if the current observation time is a thickness jump point or a thickness drop point, the method for obtaining the pressure control state eigenvalue of the current observation time is: traverse and search one by one in the reverse time direction from the current observation time, calculate the cosine similarity of the traversed observation time and the pressure control similarity vector corresponding to the current observation time, obtain the observation time corresponding to the maximum cosine similarity, and use the pressure control state eigenvalue of the observation time as the pressure control state eigenvalue of the current observation time, wherein the traversed observation time cannot be a thickness jump point or a thickness drop point; Calculate the pressure control strategy value PCSV of the oil film accumulation binary group according to the thickness jump point and thickness drop point: ; Where j1 is the serial number of the observation time, Ltco j1 is the voltage-controlled state eigenvalue corresponding to the j1th observation time, avg{} is the average value function, exp() is the exponential function with the natural constant e as the base, sigmoid is the activation function, rk() is the sorting coefficient function, and the return value obtained by the sorting coefficient function rk(j1) is: Get the percentile value of all voltage-controlled state eigenvalues ​​in the TPh period at the j1th observation time.

[0033] 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 safety pressure; setting the mapping function of the pressure adjustment amount to ΔP=α*(PCSV– M_PCSV), where 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, adjusting the PID parameters through the fuzzy control algorithm; adjusting the pressure to the sum of ΔP and the current real-time pressure value Pac, recorded as the control pressure value P CV , set the pressure to P CV ; Set the grease accumulation model to the grease accumulation amount , where β is the model adjustment parameter, with a value between 0 and 1; the safety threshold is set to OA value 12-18, with a default value of 15. If OA exceeds the safety threshold, the pressure is reduced to the minimum safety pressure and the alarm system is activated.

[0034] An embodiment of the present invention provides an electric rice cooker cooking optimization system based on an intelligent algorithm, such as Figure 2The figure shows a structure diagram of an electric cooker cooking optimization system based on an intelligent algorithm of the present invention. The electric cooker cooking optimization system based on an intelligent algorithm of this embodiment comprises: 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 in the above-mentioned electric cooker cooking optimization method embodiment based on the intelligent algorithm are implemented.

[0035] The system comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to run in the following units of the system: A sensor configuration unit, used for arranging and calibrating infrared sensors; A collection and processing unit, used for collecting data and calculating mean values ​​of the rice cooker using sensors; The data calculation and structuring unit is used to perform time-series oil film transformation on the collected mean data to form oil film accumulation binary groups; Intelligent algorithm unit, used to analyze the oil film accumulation binary array and obtain the pressure control strategy value; The control and evaluation unit is used to correct the cooking pressure according to the pressure control strategy value.

[0036] The rice cooker cooking optimization system based on intelligent algorithm can be run in computing devices such as desktop computers, laptop computers, PDAs and cloud servers. The rice cooker cooking optimization system based on intelligent algorithm can be operated on systems including, but not limited to, processors and memories. Those skilled in the art can understand that the example is only an example of a rice cooker cooking optimization system based on intelligent algorithm, and does not constitute a limitation on a rice cooker cooking optimization system based on intelligent algorithm. It can include more or fewer components than the example, or combine certain components, or different components. For example, the rice cooker cooking optimization system based on intelligent algorithm can also include input and output devices, network access devices, buses, etc.

[0037] The processor may be a central processing unit (CPU), or 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 may be a microprocessor or any conventional processor, etc. The processor is the control center of the operation system of the electric cooker cooking optimization system based on the intelligent algorithm, and various interfaces and lines are used to connect the various parts of the entire operation system of the electric cooker cooking optimization system based on the intelligent algorithm.

[0038] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the rice cooker cooking optimization system based on intelligent algorithm by running or executing the computer program and / or module 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, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0039] Although the description of the present invention has been quite detailed and has been described in particular 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 invention. In addition, the present invention is described above with the embodiments foreseeable by the inventors, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that are not currently foreseen may still represent equivalent changes of the present invention.

Claims

1. A rice cooker cooking optimization method based on intelligent algorithm, characterized in that: The method comprises the following steps: S100, arranging and calibrating infrared sensors; S200, using sensors to collect data and calculate mean values ​​of the rice cooker; S300, performing a time series oil film transformation on the collected mean value data to form an oil film accumulation binary group; S400, performing grease backlog analysis on the oil film accumulation binary array and obtaining a pressure control strategy value; S500, performing cooking pressure correction according to the pressure control strategy value; In step S400, the method for performing grease backlog analysis on the oil film accumulation binary array and obtaining the pressure control strategy value is as follows: set a time period as a monitoring period TPh, TPh∈[0.5,3] hours, collect the mean value of pressure value and the mean value of oil film thickness at equal intervals during the monitoring period, set the reference collection number SID, SID∈(30,50) times; The time scale at which the mean pressure value and the mean oil film thickness are obtained is recorded as a reference point; during the monitoring period, the mean pressure values ​​of each reference point constitute a first pressure mapping set, and the mean pressure values ​​of each reference point are smoothed using a Gaussian filter, and the processed data constitute a second pressure mapping set; Calculate the absolute residuals 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 record the reference point as the fluctuation reference point, and record the time period between any fluctuation reference point and the first non-continuous fluctuation reference point in the reverse time direction as the sub-fluctuation domain. The two-tuple consisting of the mean pressure value and the mean oil film thickness in each reference point is recorded as a strategy metric pair, and the ratio of the mean oil film thickness to the mean pressure value is recorded as the film pressure Mltg. The reference point of the strategy metric pair corresponding to the maximum value of the film pressure in each sub-fluctuation domain is obtained and recorded as a sub-fluctuation singular point; the average Euclidean distance between the sub-fluctuation singular point and all reference points in the corresponding sub-fluctuation domain is calculated and recorded as the fluctuation core metric Cmov; the pressure control strategy value of the oil film accumulation two-tuple is calculated according to each sub-fluctuation domain.

2. The method for optimizing cooking of electric rice cookers based on an intelligent algorithm 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 includes an infrared sensor and a pressure sensor, and the infrared sensor is an infrared reflection sensor; the infrared sensor is installed in the central area of ​​the inner cavity of the electric rice cooker or in any area parallel to the surface of the pressure sensor, and its installation angle is calibrated to be orthogonal to the central section of the pressure sensor surface.

3. The method for optimizing cooking of electric rice cookers based on intelligent algorithms according to claim 1, characterized in that: In step S200, the method of using the sensor to collect data and calculate the mean of the rice cooker is: setting the monitoring time interval to k0, k0∈[0.5,5] seconds, and presetting the infrared monitoring fault tolerance time IMT, IMT∈[5,10) minutes; when the rice cooker is in operation, using the pressure sensor to collect the real-time pressure value Pac every k0; when the rice cooker is changed from the operation state to the standby or insulation state, obtaining the average value of all real-time pressure values ​​as the pressure level, and starting infrared monitoring of IMT minutes: every k0 seconds, using the infrared sensor to emit infrared light and receive the infrared light beam reflected by the surface of the pressure sensor, recording the incident light intensity and the corresponding reflected light intensity, and calculating the incident light intensity mean and the reflected light intensity mean within the infrared monitoring fault tolerance time.

4. The method for optimizing cooking of electric rice cookers based on an intelligent algorithm according to claim 1, characterized in that: In step S300, the collected mean data is subjected to a time-series oil film transformation to form an oil film accumulation binary group by substituting the incident light intensity mean and the reflected light intensity mean into the reflected light intensity change formula to calculate the oil film thickness OFT; and recording a two-dimensional array consisting of the pressure level collected under the operation state of the rice cooker and the corresponding oil film thickness as an oil film accumulation binary group.

5. The method for optimizing cooking of electric rice cookers based on intelligent algorithms according to claim 1, characterized in that: In step S400, the method of performing grease backlog analysis on the oil film accumulation binary array and obtaining the pressure control strategy value can be replaced by: setting a time period as the monitoring period TPh, TPh∈[0.5,3] hours, collecting the mean pressure value and the mean oil film thickness at equal intervals during the monitoring period, setting the reference collection times SID, SID∈(30,50) times; The time scale for obtaining the mean pressure value and the mean oil film thickness is recorded as the observation time; the standard deviation of the mean oil film thickness in the oil film accumulation binary group is calculated and recorded as the thickness dispersion; within the monitoring period, if the oil film thickness mean 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; The jump binary group is composed of any thickness jump point and its corresponding oil film thickness mean value. The set constructed by the jump binary group is interpolated by cubic spline using splrep and splev functions to obtain a smooth curve. The value on the smooth curve obtained by fitting at each moment is the fitting value; the difference between the fitting value of any thickness drop point and its oil film thickness mean value is the fitting perception degree, and the root mean square ratio of the fitting perception degree of a negative number to the fitting perception degree of a positive number is calculated and recorded as the differential perception factor Dep; The average oil film thickness at all observation moments is normalized to form a thickness normalized value. The product of the average pressure value at any observation moment and the thickness normalized value is the pressure-controlled phase value Volg. The first thickness jump point and thickness drop point obtained by reverse time search at any observation moment are respectively used as the high jump tracing point and low drop tracing point at the observation moment; The pressure-controlled state eigenvalue Ltco at the observation time is calculated based on the high jump tracing point and the low drop tracing 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 voltage-controlled phase values ​​of the j1th observation moment and its corresponding high jump tracing point and low drop tracing point respectively; Take any observation moment as the current observation moment; record the mean pressure value corresponding to an observation moment, the mean oil film thickness and the pressure control phase value to form a pressure control similarity vector; if the current observation moment is a thickness jump point or a thickness drop point, then the method for obtaining the pressure control state eigenvalue of the current observation moment is: traverse and search one by one in the reverse time direction from the current observation moment, calculate the cosine similarity of the traversed observation moment and the pressure control similarity vector corresponding to the current observation moment, obtain the observation moment corresponding to the maximum cosine similarity, and use the pressure control state eigenvalue of the observation moment as the pressure control state eigenvalue of the current observation moment, wherein the traversed observation moment cannot be a thickness jump point or a thickness drop point; calculate the pressure control strategy value of the oil film accumulation binary according to the thickness jump point and the thickness drop point.

6. The method for optimizing cooking of a rice cooker based on an intelligent algorithm according to claim 1, characterized in that: 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 safety pressure; setting the mapping function of the pressure adjustment amount to ΔP=α*(PCSV– M_PCSV), where 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, adjusting the PID parameters by the fuzzy control algorithm; The pressure is adjusted to the sum of ΔP and the current real-time pressure value Pac, which is recorded as the control pressure value P CV , set the pressure to P CV .

7. A rice cooker cooking optimization system based on intelligent algorithm, characterized in that: The electric rice cooker cooking optimization system based on intelligent algorithm comprises: 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 electric rice cooker cooking optimization method based on intelligent algorithm described in any one of claims 1 to 6 are implemented. The electric rice cooker cooking optimization system based on intelligent algorithm runs on a desktop computer, a laptop computer, a PDA and a computing device in a cloud data center.

Images