An electromagnetic induction sealing control method and control system based on artificial intelligence

Abstract

The present application provides an electromagnetic induction sealing control method and control system based on artificial intelligence, which determines the fuzzy execution factor in the module execution process through all the sealing execution data; uses the membership function in the function library to perform fuzzy mapping on the historical temperature data, obtains the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determines the logical return cost of using the fuzzy logic control program based on all the fuzzy memberships; determines the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program through the logical return cost and the fuzzy execution factor; and dynamically regulates the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient. Based on the above scheme, the intelligent dynamic regulation of the input value of the fuzzy logic control program in the electromagnetic induction seal can be realized, thereby improving the stability of the electromagnetic induction seal.

Description

Technical Field

[0001] The present application relates to the technical field of electromagnetic induction sealing, and more specifically, to an electromagnetic induction sealing control method and control system based on artificial intelligence. Background Art

[0002] Electromagnetic induction sealing is a technology that uses the principle of electromagnetic induction to seal containers. Electromagnetic induction sealing is mainly used in food, medicine, cosmetics and other industries to ensure product quality and safety. The principle of electromagnetic induction sealing is that the induction coil generates an alternating electromagnetic field under the action of high-frequency current. The electromagnetic induction sealing machine uses a high-frequency electromagnetic field to act on the sealing material with an aluminum foil layer, causing the aluminum foil layer to heat up rapidly, thereby melting the sealing material and achieving sealing.

[0003] In the prior art, the control of the input temperature in electromagnetic induction sealing usually adopts a typical proportional-integral-differential control algorithm. Since there is a nonlinear and uncertain relationship between the input temperature and the output temperature (i.e., the sealing temperature) in the electromagnetic induction sealing control, the proportional-integral-differential control algorithm has a reduced sealing control accuracy under the interference of this relationship, resulting in poor sealing stability of the control algorithm. The use of fuzzy logic control method can eliminate the interference factors caused by the nonlinear and uncertain relationship between the input temperature and the output temperature (i.e., the sealing temperature), thereby effectively reducing the overshoot and fluctuation value in the electromagnetic induction sealing process and improving the stability of the electromagnetic induction sealing. Therefore, how to intelligently and dynamically control the input value of the fuzzy logic control program in the electromagnetic induction sealing to improve the stability of the electromagnetic induction sealing is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an electromagnetic induction sealing control method and control system based on artificial intelligence, which can realize intelligent dynamic regulation of the input value of the fuzzy logic control program in the electromagnetic induction sealing, thereby improving the stability of the electromagnetic induction sealing.

[0005] In a first aspect, the present application provides an electromagnetic induction sealing control method based on artificial intelligence, comprising:

[0006] Collect the execution records of the program execution device during the electromagnetic induction sealing process, and then obtain the historical execution data;

[0007] Extracting the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing from the historical execution data, and then determining the fuzzy execution factor in the module execution process through all the sealing execution data;

[0008] Acquire historical temperature data in the electromagnetic induction sealing process from the historical execution data, perform fuzzy mapping on the historical temperature data using the membership function in the function library, obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determine the logic return cost of using the fuzzy logic control program based on all the fuzzy memberships;

[0009] Determine the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program to perform electromagnetic induction sealing through the logic return cost and the fuzzy execution factor;

[0010] The input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware is dynamically adjusted based on the execution compensation coefficient.

[0011] In some embodiments, determining the fuzzy execution factor during the module execution process through all sealed execution data specifically includes:

[0012] Extracting the temperature characteristics of the artificial intelligence middleware when performing each fuzzy logic processing from the sealing execution data, and then determining the temperature characteristic vector;

[0013] Determine the temperature fuzziness of the artificial intelligence middleware after processing by the corresponding sealing execution module based on each sealing execution data;

[0014] The fuzzy execution factor of the artificial intelligence middleware on the sealing temperature is determined by the temperature feature vector and all temperature fuzziness.

[0015] In some embodiments, using the membership function in the function library to perform fuzzy mapping on the historical temperature data to obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program specifically includes:

[0016] Collect all input temperatures in the historical temperature data to obtain multiple temperature fuzzy intervals;

[0017] Map each input temperature in the historical temperature data to a corresponding temperature fuzzy interval to obtain a fuzzy mapping domain;

[0018] Mapping and judging each input temperature is performed through the fuzzy mapping domain and the membership function in the function library to obtain the fuzzy membership degree corresponding to each input temperature in the historical temperature data.

[0019] In some embodiments, determining the logic return cost of using the fuzzy logic control program based on all fuzzy memberships specifically includes:

[0020] Determine the fuzzy boundary of the output temperature after electromagnetic induction sealing through all fuzzy membership degrees;

[0021] Screening out fuzzy typical values ​​from all fuzzy membership degrees, and then determining the output typical value of the output temperature after electromagnetic induction sealing through the fuzzy typical values;

[0022] The logic return cost of the fuzzy logic control program is obtained through the output typical value and the fuzzy boundary.

[0023] In some embodiments, determining the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing by using the logic return cost and the fuzzy execution factor specifically includes:

[0024] Obtain the sealing temperature record during the electromagnetic induction sealing process;

[0025] For each sealing temperature in the sealing temperature record, obtaining a historical input temperature corresponding to the sealing temperature in the historical temperature data;

[0026] Obtaining an input temperature corresponding to the sealing temperature in the sealing temperature record, and then determining an input temperature difference between the historical input temperature and the input temperature;

[0027] Determine the hysteresis temperature difference of the sealing temperature by using the logic return cost and the input temperature difference, and then obtain the hysteresis temperature difference of each sealing temperature in the sealing temperature record;

[0028] The execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing is determined according to all hysteresis temperature differences and the fuzzy execution factor.

[0029] In some embodiments, performing fuzzy compensation on each sealing temperature in the sealing temperature record by executing the compensation coefficient to obtain all sealing compensation temperatures specifically includes:

[0030] For each sealing temperature in the sealing temperature record, determining an execution error according to the execution compensation coefficient and the sealing temperature;

[0031] The sealing temperature is compensated using the execution error to obtain the sealing compensation temperature, and then all the sealing compensation temperatures are determined.

[0032] In some embodiments, dynamically adjusting the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient specifically includes:

[0033] Performing fuzzy compensation on each sealing temperature in the sealing temperature record by using the execution compensation coefficient to obtain all sealing compensation temperatures;

[0034] The input temperature of the program execution device in the electromagnetic induction sealing process is regulated based on the execution error in each fuzzy compensation and the corresponding sealing compensation temperature.

[0035] In a second aspect, the present application provides an electromagnetic induction sealing control system based on artificial intelligence, including a sealing control unit, wherein the sealing control unit includes:

[0036] An acquisition module is used to collect the execution records of the program execution device during the electromagnetic induction sealing process, and then obtain historical execution data;

[0037] A processing module, used to extract, from the historical execution data, the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing, and then determine the fuzzy execution factor in the module execution process through all the sealing execution data;

[0038] The processing module is also used to obtain historical temperature data in the electromagnetic induction sealing process from the historical execution data, use the membership function in the function library to perform fuzzy mapping on the historical temperature data, obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determine the logic return cost of using the fuzzy logic control program based on all the fuzzy memberships;

[0039] The processing module is also used to determine the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program to perform electromagnetic induction sealing through the logic return cost and the fuzzy execution factor;

[0040] The sealing execution module is used to dynamically adjust the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient.

[0041] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned electromagnetic induction sealing control method based on artificial intelligence.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned electromagnetic induction sealing control method based on artificial intelligence when executing.

[0043] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0044] In an electromagnetic induction sealing control method and control system based on artificial intelligence provided by the present application, the execution records of the program execution device in the electromagnetic induction sealing process are collected to obtain historical execution data; the sealing execution data of each sealing execution module of the artificial intelligence middleware in the program execution device when executing the fuzzy logic control program of electromagnetic induction sealing is extracted from the historical execution data, and the fuzzy execution factor in the module execution process is determined through all the sealing execution data; the historical temperature data in the electromagnetic induction sealing process is obtained from the historical execution data, and the historical temperature data is fuzzily mapped using the membership function in the function library to obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then the logic return cost of using the fuzzy logic control program is determined based on all the fuzzy memberships; the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing is determined through the logic return cost and the fuzzy execution factor; the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware is dynamically adjusted based on the execution compensation coefficient.

[0045] It can be seen that in the present application, the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware is dynamically regulated based on the execution compensation coefficient; first, determining the fuzzy execution factor can obtain the fuzziness degree of the sealing temperature after the input temperature is subjected to fuzzy logic processing, which can facilitate the subsequent adjustment of the input temperature in the electromagnetic induction sealing process by comprehensively considering the fuzziness degree to reduce the error of the sealing temperature, thereby ensuring the stability of the output temperature; secondly, determining the logic return cost can obtain a quantitative value of the degree of temperature loss between the output temperature and the expected output temperature, which can be used to comprehensively consider the degree of temperature loss in the subsequent period to obtain a more accurate output error, thereby The output error is compensated to improve the stability of the final sealing temperature (i.e., output temperature); then, the fuzziness degree of the sealing temperature after fuzzy logic processing (i.e., fuzzy execution factor) and the temperature loss degree between the output temperature and the expected output temperature (logic return cost) are comprehensively considered to determine the execution compensation coefficient between the historical temperature and the current sealing temperature, which can realize the error correction of the real-time temperature in the current sealing process, thereby further improving the stability of the sealing temperature, and thus improving the stability of the electromagnetic induction sealing; in summary, based on the above scheme, the intelligent dynamic regulation of the input value of the fuzzy logic control program in the electromagnetic induction sealing can be realized, thereby improving the stability of the electromagnetic induction sealing. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0047] Figure 1 is an exemplary flow chart of an electromagnetic induction sealing control method based on artificial intelligence according to some embodiments of the present application;

[0048] Figure 2 is a schematic diagram of a process for determining a fuzzy execution factor according to some embodiments of the present application;

[0049] Figure 3 is a schematic diagram of a process for determining fuzzy membership according to some embodiments of the present application;

[0050] Figure 4 is a schematic diagram of exemplary hardware and / or software of a sealing control unit according to some embodiments of the present application;

[0051] Figure 5 It is a structural schematic diagram of a computer device that applies an electromagnetic induction sealing control method based on artificial intelligence as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] The embodiment of the present application provides an electromagnetic induction sealing control method and control system based on artificial intelligence, the core of which is to determine the fuzzy execution factor in the module execution process through all the sealing execution data; use the membership function in the function library to fuzzy map the historical temperature data to obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determine the logical return cost of using the fuzzy logic control program based on all the fuzzy memberships; determine the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program through the logical return cost and the fuzzy execution factor; and dynamically control the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient. Based on the above scheme, the intelligent dynamic control of the input value of the fuzzy logic control program in the electromagnetic induction seal can be realized, thereby improving the stability of the electromagnetic induction seal.

[0054] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of an electromagnetic induction sealing control method based on artificial intelligence according to some embodiments of the present application, and the electromagnetic induction sealing control method based on artificial intelligence mainly includes the following steps:

[0055] In step 101, the execution records of the program execution device during the electromagnetic induction sealing process are collected to obtain historical execution data.

[0056] It should be noted that, in the present application, the program execution device refers to a device for executing the electromagnetic induction sealing process control program; in specific implementation, the execution record of the electromagnetic induction sealing process within a preset time period (the default is 10 days) can be obtained in the program execution device, and the collection of all execution records can be used as historical execution data. It should be noted that, in the present application, the execution record contains input temperature, output temperature, temperature conversion process data and sealing delay, wherein the sealing delay refers to the execution delay between input and output, and the time interval between the first input temperature and the first output temperature change can be used as the sealing delay; the temperature conversion process data refers to data composed of the process temperature values ​​of the electromagnetic induction sealing control program converting the input temperature into the output temperature.

[0057] In step 102, the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing is extracted from the historical execution data, and then the fuzzy execution factor in the module execution process is determined through all the sealing execution data.

[0058] It should be noted that, in the present application, artificial intelligence middleware refers to the intermediate layer software used by the program execution device in the electromagnetic induction sealing to connect the conversion relationship between the input temperature and the output temperature; the sealing execution data represents the process data for fuzzy logic control. The fuzzy logic control in the present application is a control method for the electromagnetic induction sealing temperature based on fuzzy set theory. The fuzzy logic control can handle the nonlinear and uncertain relationship between the input temperature and the output temperature that is difficult to solve by traditional control methods; the sealing execution module refers to a module composed of all execution programs used by the fuzzy logic control program for each temperature adjustment during the electromagnetic induction sealing process. Since the temperature needs to be dynamically adjusted during the electromagnetic induction sealing process, there are multiple (two or more) input-to-output conversion processes (ie, sealing execution modules) in one electromagnetic induction sealing process, and each sealing execution module represents a conversion process between the input temperature and the output temperature.

[0059] In some embodiments, extracting the sealing execution data of each sealing execution module in the program execution device when the artificial intelligence middleware executes the fuzzy logic control program of electromagnetic induction sealing in the historical execution data can be achieved by using the following steps:

[0060] For each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing, extracting the sealing execution record of each electromagnetic induction sealing process in the sealing execution module in the historical execution data;

[0061] The sealing execution data of the sealing execution module is determined through all the sealing execution records, and then the sealing execution data of each sealing execution module of the artificial intelligence middleware in the program execution device when executing the fuzzy logic control program of electromagnetic induction sealing is obtained.

[0062] In the specific implementation, first, a sealing execution module is selected, and for each electromagnetic induction sealing, the execution record of the electromagnetic induction sealing process is obtained in the historical execution data, and the temperature conversion process record corresponding to the sealing execution module in the execution record can be used as the sealing execution record corresponding to the sealing execution module in the electromagnetic induction sealing process. The sealing execution record corresponding to the sealing execution module in each electromagnetic induction sealing process can be obtained in the above manner; then, the collection of all sealing execution records can be used as the sealing execution data of the sealing execution module, and the above steps are repeated to obtain the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing.

[0063] In some embodiments, the fuzzy execution factor during the module execution process is determined by all the sealed execution data, referring to Figure 2 The figure is a schematic diagram of a process for determining a fuzzy execution factor in some embodiments of the present application. In this embodiment, the fuzzy execution factor can be determined by the following steps:

[0064] In step 1021, the temperature characteristics of the artificial intelligence middleware when performing each fuzzy logic processing are extracted from all the sealing execution data, and then the temperature characteristic vector is determined;

[0065] In step 1022, the temperature fuzziness of the artificial intelligence middleware after being processed by the corresponding sealing execution module is determined according to each sealing execution data;

[0066] In step 1023, the fuzzy execution factor of the artificial intelligence middleware for the sealing temperature is determined by the temperature feature vector and all temperature fuzziness.

[0067] It should be noted that, in the present application, the fuzzy execution factor represents the degree of fuzziness of the sealing temperature after the fuzzy logic program is executed on the input temperature. The fuzzy execution factor is used to adjust the input temperature in the electromagnetic induction sealing process to ensure the stability of the output temperature. In specific implementation, in some embodiments, the following method can be used: First, for each fuzzy logic program execution process performed by the artificial intelligence middleware, the sealing execution data used to describe the fuzzy logic program execution process is obtained from all the sealing execution data. The existing temperature feature extraction algorithm (for example, principal component analysis) can be used to extract the characteristic values ​​of all process temperature values ​​in the sealing execution record as temperature features. The temperature features of each fuzzy logic processing performed by the artificial intelligence middleware can be obtained in the above manner, and the set of all temperature features can be used as a temperature feature vector; then, for each sealing execution data , obtain the input temperature and output temperature in the sealing execution data, take the natural logarithm of the absolute value of the difference between each process temperature value in the sealing execution data and the output temperature as the output deviation of the output temperature and the corresponding process temperature value, take the natural logarithm of the absolute value of the difference between each process temperature value in the sealing execution record and the input temperature as the conversion deviation of the output temperature and the corresponding process temperature value, the ratio of the output deviation to the corresponding conversion deviation can be used as the logarithmic deviation of the corresponding process temperature value, the standard deviation of all logarithmic deviations can be used as the temperature fuzziness after the sealing execution module corresponding to the sealing execution data is processed, and the temperature fuzziness of the artificial intelligence middleware after each sealing execution module processing can be obtained by the above method; finally, the ratio of the standard deviation of all temperature features in the temperature feature vector to the mean of all temperature fuzziness can be used as the fuzzy execution factor of the artificial intelligence middleware for the sealing temperature. In other embodiments, other methods can also be used for implementation, which is not limited here.

[0068] It should be noted that, in the present application, the output deviation refers to the logarithmic deviation between the process temperature value and the output temperature; the conversion deviation refers to the deviation value in the conversion process from the input temperature to the process temperature value.

[0069] In step 103, historical temperature data during the electromagnetic induction sealing process is obtained from the historical execution data, and the historical temperature data is fuzzy mapped using the membership function in the function library to obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then the logical return cost of using the fuzzy logic control program is determined based on all the fuzzy memberships.

[0070] In specific implementation, the input temperature of each execution record in the historical execution data is obtained, and the set of all input temperatures can be used as the historical temperature data in the electromagnetic induction sealing process; wherein the historical temperature data represents data composed of input temperature values ​​in the execution process of the electromagnetic induction sealing control program.

[0071] It should be noted that in the present application, the fuzzy membership degree indicates the degree to which the input temperature belongs to a temperature fuzzy interval; the membership function is a data mapping method, which can map an input value to a value between 0 and 1. In the present application, the value between 0 and 1 is the fuzzy membership degree. A fuzzy membership degree of 0 indicates that the element does not belong to the temperature fuzzy zone at all, and a fuzzy membership degree of 1 indicates that the element completely belongs to the temperature fuzzy zone.

[0072] In some embodiments, the historical temperature data is fuzzily mapped using the membership function in the function library to obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program. Figure 3 As described above, the figure is a schematic diagram of the process of determining the fuzzy membership in some embodiments of the present application. In this embodiment, the fuzzy membership can be determined by the following steps:

[0073] In step 1031, all input temperatures in the historical temperature data are aggregated to obtain a plurality of temperature fuzzy intervals;

[0074] In step 1032, each input temperature in the historical temperature data is mapped to a corresponding temperature fuzzy interval to obtain a fuzzy mapping domain;

[0075] In step 1033, mapping and judging are performed on each input temperature through the fuzzy mapping domain and the membership function in the function library to obtain the fuzzy membership degree corresponding to each input temperature in the historical temperature data.

[0076] It should be noted that, in the present application, the temperature fuzzy interval is an interval that describes different temperature ranges. Different temperature fuzzy intervals have intersections, and there is a many-to-many data relationship between the temperature fuzzy interval and the input temperature, that is, each temperature fuzzy interval contains multiple input temperatures, and each input temperature can also exist in multiple temperature fuzzy intervals. The above-mentioned many-to-many data relationship facilitates the subsequent comprehensive analysis of the fuzzy membership of each input temperature relative to the temperature fuzzy interval to obtain a more accurate logical return cost; the fuzzy mapping domain is a mapping space that contains the mapping relationship between each input temperature and the temperature fuzzy interval.

[0077] In the specific implementation, first, the existing induction algorithm (for example, decision tree regression algorithm) can be used to collect all the input temperatures in the historical temperature data to obtain multiple temperature fuzzy intervals; then, each input temperature in the historical temperature data can be mapped to the corresponding temperature fuzzy interval according to the temperature range of the temperature fuzzy interval, and the set of all mapped temperature fuzzy intervals is used as the fuzzy mapping domain; finally, for each input temperature in the historical temperature data, all temperature fuzzy intervals corresponding to the input temperature in the fuzzy mapping domain are obtained, and the membership function in the function library can be used to map the input temperature to the membership value of each temperature fuzzy interval, and all the membership values ​​can be used as the value range of the fuzzy membership degree corresponding to the input temperature to complete the mapping judgment of the input temperature. The fuzzy membership degree corresponding to each input temperature in the historical temperature data can be obtained in the above manner.

[0078] In some embodiments, determining the logic return cost of using the fuzzy logic control program based on all fuzzy memberships can be implemented by the following steps:

[0079] Determine the fuzzy boundary of the output temperature after electromagnetic induction sealing through all fuzzy membership degrees;

[0080] Screening out fuzzy typical values ​​from all fuzzy membership degrees, and then determining the output typical value of the output temperature after electromagnetic induction sealing through the fuzzy typical values;

[0081] The logic return cost of the fuzzy logic control program is obtained through the output typical value and the fuzzy boundary.

[0082] It should be noted that the logical return cost represents the quantitative value of the temperature loss degree between the return data and the expected output temperature after the fuzzy logic control program is executed. The greater the absolute value of the difference between the logical return cost and 0, the greater the temperature loss degree between the output temperature and the expected output temperature. A logical return cost of 0 indicates that there is no deviation in the output temperature; a negative logical return cost indicates that the output temperature is too high; a positive logical return cost indicates that the logical return cost is too low. In specific implementation, first, initialize a membership interval, take the maximum value of all fuzzy memberships as the upper bound of the membership interval, and take the minimum value of all fuzzy memberships as the lower bound of the membership interval. This membership interval is used as the fuzzy boundary of the output temperature after electromagnetic induction sealing; then, the mode of all fuzzy membership degrees can be used as the fuzzy typical value to obtain the input temperature corresponding to the fuzzy typical value, and then all execution records with the same input temperature are obtained in the historical execution data, and the average of the output temperatures in all the above execution records can be used as the output typical value of the output temperature after electromagnetic induction sealing; finally, the difference between the output typical value and the upper boundary in the fuzzy boundary is used as the upper deviation value, and the difference between the output typical value and the lower boundary in the fuzzy boundary is used as the lower deviation value, and the difference between the upper deviation value and the lower deviation value can be used as the logic return cost of the fuzzy logic control program.

[0083] In step 104, the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program to perform electromagnetic induction sealing is determined by using the logic return cost and the fuzzy execution factor.

[0084] It should be noted that in the present application, the input temperature is adjusted in real time through the sealing program during the electromagnetic induction sealing process to ensure the effectiveness of the output temperature, and the initial input temperature is set according to historical experience at the beginning stage of electromagnetic induction sealing (i.e., there is no sealing temperature record); in specific implementation, each output temperature in this electromagnetic induction sealing process is used as the sealing temperature, and the set of all sealing temperatures can be used as the sealing temperature record, wherein the sealing temperature record also includes the input temperature corresponding to each sealing temperature.

[0085] In some embodiments, determining the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing by using the logic return cost and the fuzzy execution factor can be implemented by the following steps:

[0086] Obtain the sealing temperature record during the electromagnetic induction sealing process;

[0087] For each sealing temperature in the sealing temperature record, obtaining a historical input temperature corresponding to the sealing temperature in the historical temperature data;

[0088] Obtaining an input temperature corresponding to the sealing temperature in the sealing temperature record, and then determining an input temperature difference between the historical input temperature and the input temperature;

[0089] Determine the hysteresis temperature difference of the sealing temperature by using the logic return cost and the input temperature difference, and then obtain the hysteresis temperature difference of each sealing temperature in the sealing temperature record;

[0090] The execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing is determined according to all hysteresis temperature differences and the fuzzy execution factor.

[0091] It should be noted that, in the present application, the execution compensation coefficient is a proportional coefficient used by the fuzzy logic control program to compensate for the error of the sealing temperature. The execution compensation coefficient can realize the temperature compensation process by determining the error of the sealing temperature. In the specific implementation, first, the sealing temperature record in the electromagnetic induction sealing process is obtained; secondly, for each sealing temperature in the sealing temperature record, the historical input temperature corresponding to the sealing temperature is obtained in the historical temperature data; then, the input temperature corresponding to the sealing temperature is obtained in the sealing temperature record, and the difference between the historical input temperature and the input temperature can be used as the input temperature difference; and then However, the difference between the logic return cost and the input temperature difference can be used as the hysteresis temperature difference of the sealing temperature. The hysteresis temperature difference refers to the quantified value of the reaction hysteresis characteristics within different temperature ranges. The hysteresis temperature difference of each sealing temperature in the sealing temperature record can be obtained in the above manner. Finally, for each hysteresis temperature difference, the product of the hysteresis temperature difference and the fuzzy execution factor can be used as the compensation value corresponding to the hysteresis temperature difference. The compensation value corresponding to each hysteresis temperature difference can be obtained in the above manner. All compensation values ​​are used as the value range of the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing.

[0092] In step 105, the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware is dynamically adjusted based on the execution compensation coefficient.

[0093] In some embodiments, dynamically adjusting the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient can be achieved by the following steps:

[0094] Performing fuzzy compensation on each sealing temperature in the sealing temperature record by using the execution compensation coefficient to obtain all sealing compensation temperatures;

[0095] The input temperature of the program execution device in the electromagnetic induction sealing process is regulated based on the execution error in each fuzzy compensation and the corresponding sealing compensation temperature.

[0096] Preferably, in the above embodiment, fuzzy compensation is performed on each sealing temperature in the sealing temperature record by executing the compensation coefficient, and all sealing compensation temperatures can be obtained by the following steps:

[0097] For each sealing temperature in the sealing temperature record, determining an execution error according to the execution compensation coefficient and the sealing temperature;

[0098] The sealing temperature is compensated using the execution error to obtain the sealing compensation temperature, and then all the sealing compensation temperatures are determined.

[0099] In the specific implementation, first, for each sealing temperature in the sealing temperature record, the compensation value of the sealing temperature in the execution compensation coefficient is obtained, and the product of the compensation value and the sealing temperature can be used as the execution error; then, the execution error can be used as the temperature compensation value of the sealing temperature to complete the compensation process of the sealing temperature, that is: the sum of the execution error and the sealing temperature can be used as the sealing compensation temperature, and all sealing compensation temperatures can be obtained in the above manner.

[0100] Preferably, in the above embodiment, the input temperature of the program execution device in the electromagnetic induction sealing process is regulated based on the execution error in each fuzzy compensation and the corresponding sealing compensation temperature, which can be achieved by adopting the following steps:

[0101] Initialize a control model, and use each sealing compensation temperature and the corresponding execution error as the training basis of the control model;

[0102] Obtaining a target sealing temperature, and then using the target sealing temperature as a target value of a control model;

[0103] The control model is used to control the input temperature of the program execution device.

[0104] In the specific implementation, first, a control model is initialized, and each sealing compensation temperature and the corresponding execution error are used as the training basis of the control model. The training of the control model can be completed in combination with the usage scenario, so that a more accurate input temperature can be obtained through the trained control model, thereby ensuring the stability of the final sealing temperature. Then, the target sealing temperature is obtained, and the target sealing temperature is used as the target value of the control model; finally, the execution result of the control model can be used as the input temperature of the program execution device. In other embodiments, other methods can also be used to implement it, which is not limited in this application.

[0105] In the present application, the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware is dynamically controlled based on the execution compensation coefficient; firstly, the fuzzy execution factor is determined to obtain the fuzziness degree of the sealing temperature after the fuzzy logic processing of the input temperature, which can facilitate the subsequent adjustment of the input temperature in the electromagnetic induction sealing process by comprehensively considering the fuzziness degree to reduce the error of the sealing temperature, thereby ensuring the stability of the output temperature; secondly, the logic return cost is determined to obtain a quantitative value of the temperature loss degree between the output temperature and the expected output temperature, which can be used to comprehensively consider the temperature loss degree in the subsequent output to obtain a more accurate output error, thereby The error is compensated to improve the stability of the final sealing temperature (i.e., output temperature); then, the fuzziness degree of the sealing temperature after fuzzy logic processing (i.e., fuzzy execution factor) and the temperature loss degree between the output temperature and the expected output temperature (logic return cost) are comprehensively considered to determine the execution compensation coefficient between the historical temperature and the current sealing temperature, which can realize the error correction of the real-time temperature in the current sealing process, thereby further improving the stability of the sealing temperature, that is, improving the stability of the electromagnetic induction sealing; in summary, based on the above scheme, the intelligent dynamic regulation of the input value of the fuzzy logic control program in the electromagnetic induction sealing can be realized, thereby improving the stability of the electromagnetic induction sealing.

[0106] In addition, in another aspect of the present application, in some embodiments, the present application provides an electromagnetic induction sealing control system based on artificial intelligence, and the electromagnetic induction sealing control system based on artificial intelligence also includes a sealing control unit, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a sealing control unit according to some embodiments of the present application, the sealing control unit includes: an acquisition module 201, a processing module 202 and a sealing execution module 203, which are described as follows:

[0107] Acquisition module 201, in this application, acquisition module 201 is mainly used to collect execution records of the program execution device during the electromagnetic induction sealing process, and then obtain historical execution data;

[0108] The processing module 202 in the present application is used to extract the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing from the historical execution data, and then determine the fuzzy execution factor in the module execution process through all the sealing execution data;

[0109] It should be noted that the processing module 202 is also used to obtain historical temperature data in the electromagnetic induction sealing process from the historical execution data, use the membership function in the function library to perform fuzzy mapping on the historical temperature data, obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determine the logic return cost of using the fuzzy logic control program based on all the fuzzy memberships;

[0110] In addition, the processing module 202 is also used to determine the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program to perform electromagnetic induction sealing through the logic return cost and the fuzzy execution factor;

[0111] The sealing execution module 203 in the present application is mainly used to dynamically adjust the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient.

[0112] The above describes in detail the examples of electromagnetic induction sealing control methods and control systems based on artificial intelligence provided by the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding devices include hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0113] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned electromagnetic induction sealing control method based on artificial intelligence.

[0114] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional, and the figure is a schematic diagram of the structure of a computer device for implementing an electromagnetic induction sealing control method based on artificial intelligence according to an embodiment of the present application. The electromagnetic induction sealing control method based on artificial intelligence described in the above embodiment can be Figure 5 The computer device shown in the figure is implemented, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device can be a terminal device, a server or a chip.

[0115] The processor 301 may be a general-purpose processor or a special-purpose processor. For example, the processor 301 may be a central processing unit (CPU), which may be used to control the computer device, execute software programs, and process data of the software programs. The computer device may also include a communication unit 305 to implement signal input (reception) and output (transmission).

[0116] For example, the computer device may be a chip, the communication unit 305 may be an input and / or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0117] For another example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0118] The computer device may include one or more memories 302, on which a program 304 is stored. The program 304 can be executed by the processor 301 to generate instructions 303, so that the processor 301 performs the method described in the above method embodiment according to the instructions 303. Optionally, data (such as a target audit model) can also be stored in the memory 302. Optionally, the processor 301 can also read the data stored in the memory 302, and the data can be stored at the same storage address as the program 304, or the data can be stored at a different storage address from the program 304.

[0119] The processor 301 and the memory 302 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0120] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0121] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0122] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned electromagnetic induction sealing control method based on artificial intelligence when executing.

[0123] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0124] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. An electromagnetic induction sealing control method based on artificial intelligence, characterized in that: The steps include: Collect the execution records of the program execution device during the electromagnetic induction sealing process, and then obtain the historical execution data; Extracting the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing from the historical execution data, and then determining the fuzzy execution factor in the module execution process through all the sealing execution data; Acquire historical temperature data in the electromagnetic induction sealing process from the historical execution data, perform fuzzy mapping on the historical temperature data using the membership function in the function library, obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determine the logic return cost of using the fuzzy logic control program based on all the fuzzy memberships; Determine the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program to perform electromagnetic induction sealing through the logic return cost and the fuzzy execution factor; Dynamically regulating the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient; Among them, the fuzzy execution factors determined during the module execution process through all the sealed execution data specifically include: Extract the temperature characteristics of the artificial intelligence middleware during each fuzzy logic processing from all the sealing execution data, and then determine the temperature characteristic vector; Determine the temperature fuzziness of the artificial intelligence middleware after processing by the corresponding sealing execution module based on each sealing execution data; Determine the fuzzy execution factor of the artificial intelligence middleware on the sealing temperature through the temperature feature vector and all temperature fuzziness; Among them, determining the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing through the logic return cost and the fuzzy execution factor specifically includes: Obtain the sealing temperature record during the electromagnetic induction sealing process; For each sealing temperature in the sealing temperature record, obtaining a historical input temperature corresponding to the sealing temperature in the historical temperature data; Obtaining an input temperature corresponding to the sealing temperature in the sealing temperature record, and then determining an input temperature difference between the historical input temperature and the input temperature; Determine the hysteresis temperature difference of the sealing temperature by using the logic return cost and the input temperature difference, and then obtain the hysteresis temperature difference of each sealing temperature in the sealing temperature record; The execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program for electromagnetic induction sealing is determined according to all hysteresis temperature differences and the fuzzy execution factor.

2. The method according to claim 1, characterized in that Using the membership function in the function library to perform fuzzy mapping on the historical temperature data to obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program specifically includes: Collect all input temperatures in the historical temperature data to obtain multiple temperature fuzzy intervals; Map each input temperature in the historical temperature data to a corresponding temperature fuzzy interval to obtain a fuzzy mapping domain; Mapping and judging each input temperature is performed through the fuzzy mapping domain and the membership function in the function library to obtain the fuzzy membership degree corresponding to each input temperature in the historical temperature data.

3. The method according to claim 1, characterized in that Determining the logic return cost of using the fuzzy logic control program based on all fuzzy memberships specifically includes: Determine the fuzzy boundary of the output temperature after electromagnetic induction sealing through all fuzzy membership degrees; Screening out fuzzy typical values ​​from all fuzzy membership degrees, and then determining the output typical value of the output temperature after electromagnetic induction sealing through the fuzzy typical values; The logic return cost of the fuzzy logic control program is obtained through the output typical value and the fuzzy boundary.

4. The method according to claim 1, characterized in that Dynamically adjusting the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient specifically includes: Performing fuzzy compensation on each sealing temperature in the sealing temperature record by using the execution compensation coefficient to obtain all sealing compensation temperatures; The input temperature of the program execution device in the electromagnetic induction sealing process is regulated based on the execution error in each fuzzy compensation and the corresponding sealing compensation temperature.

5. The method according to claim 4, characterized in that By performing fuzzy compensation on each sealing temperature in the sealing temperature record through the execution compensation coefficient, all sealing compensation temperatures are obtained, specifically including: For each sealing temperature in the sealing temperature record, determining an execution error according to the execution compensation coefficient and the sealing temperature; The sealing temperature is compensated using the execution error to obtain the sealing compensation temperature, and then all the sealing compensation temperatures are determined.

6. An electromagnetic induction sealing control system based on artificial intelligence, which adopts the method described in any one of claims 1 to 5 to perform electromagnetic induction sealing control, and the electromagnetic induction sealing control system based on artificial intelligence includes a sealing control unit, characterized in that: The sealing control unit comprises: An acquisition module is used to collect the execution records of the program execution device during the electromagnetic induction sealing process, and then obtain historical execution data; A processing module, used to extract, from the historical execution data, the sealing execution data of each sealing execution module when the artificial intelligence middleware in the program execution device executes the fuzzy logic control program of electromagnetic induction sealing, and then determine the fuzzy execution factor in the module execution process through all the sealing execution data; The processing module is also used to obtain historical temperature data in the electromagnetic induction sealing process from the historical execution data, use the membership function in the function library to perform fuzzy mapping on the historical temperature data, obtain the fuzzy membership corresponding to each input value in the fuzzy logic control program, and then determine the logic return cost of using the fuzzy logic control program based on all the fuzzy memberships; The processing module is also used to determine the execution compensation coefficient of the artificial intelligence middleware when executing the fuzzy logic control program to perform electromagnetic induction sealing through the logic return cost and the fuzzy execution factor; The sealing execution module is used to dynamically adjust the input value of each sealing execution module of the fuzzy logic control program in the artificial intelligence middleware based on the execution compensation coefficient.

7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the electromagnetic induction sealing control method based on artificial intelligence described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the electromagnetic induction sealing control method based on artificial intelligence as described in any one of claims 1 to 5.

Images