System and method for radio frequency tempering, heating, defrosting, and thawing of sensible materials using adaptive frequency and power control with infrared and visual camera monitoring

Abstract

Heating system (100) for heating an object (10), comprising: a chamber (110) for holding the object; and an RF source (120) arranged for radiating RF energy into the chamber for heating the object; wherein the RF source comprises: a frequency input (121) for adapting a frequency of the radiated RF energy; and a magnitude input (122) for adapting a magnitude of the radiated RF energy; wherein the heating system further comprises: a visual camera (130) arranged for recording a visual pattern of the object; an infrared camera (140) arranged for recording a heat pattern of the object; and a controller (150) arranged for: retrieving (230) a heating pattern for the object; receiving (210) a recorded visual pattern; starting with low-power looping comprising: receiving (220) a recorded low-power heat pattern; generating (240) a frequency setting and a low-magnitude setting while adapting the frequency setting based on the recorded visual pattern and the recorded low-power heat pattern; transmitting (250) the frequency setting and the low-magnitude setting to the frequency input and the magnitude input, respectively; and deciding to loop, to stop or to continue with high-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object; and continuing with high-power looping comprising: receiving a recorded heat pattern; generating with a high magnitude setting while maintaining the applicable frequency setting found during the low-power looping; transmitting the frequency setting and the high-magnitude setting to the frequency input and the magnitude input, respectively; and deciding to loop, to stop or to continue with low-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object.

Description

[0001] SYSTEM AND METHOD FOR RADIO FREQUENCY TEMPERING, HEATING, DEFROSTING, AND THAWING

[0002] OF SENSIBLE MATERIALS USING ADAPTIVE FREQUENCY AND POWER CONTROL WITH INFRARED AND VISUAL CAMERA MONITORING

[0003] FIELD OF THE INVENTION

[0004] The invention relates to a heating system. The invention further relates to a method for heating an object. The invention further relates to a computer program product, and a neural network trainer for heating systems or methods for heating an object.

[0005] BACKGROUND OF THE INVENTION

[0006] CN113840411 discloses a microwave oven which comprises a microwave oven body and a vertical hinged door rotationally connected to the microwave oven body, and a magnetron for generating microwaves and a turntable for driving food to rotate are arranged in the microwave oven body. A temperature sensing device used for sensing the temperature in the microwave oven body is arranged on the inner wall of the microwave oven body, an infrared thermal imaging camera is arranged at the top in the microwave oven body, and the infrared thermal imaging camera is connected with or internally provided with an image recognition module used forjudging the temperature and the size of food. The image recognition module is connected with a control module for controlling the power and the heating time of the microwave oven according to the temperature and the size of food. According to the disclosed microwave oven, after a user puts food into the rotating disc, the control module can automatically control the heating power and the heating time of the microwave oven according to the preset data according to the temperature and the size of the food. A disadvantage of the disclosed microwave oven is that the heat in the food is not evenly spread when quickly heating the food. Furthermore, the unevenness of the heat in the food more quickly rises when the food is heated quicker. Furthermore, a conventional microwave requires additional mechanical parts for a rotating plate for obtaining a somewhat even heating of the food.

[0007] A further disclosure is US 2022 / 264709 A1 disclosing an adaptive cooking device that includes: a cooking chamber configured to receive a food product, an antenna assembly, an RF power source, a sensor assembly coupled to the cooking chamber and comprising a plurality of sensors, each sensor configured to obtain a measurement characterizing a cooking process in real-time, and one or more sensors of the plurality of sensors configured to obtain a different type of the measurement, and a controller coupled to the antenna assembly, the sensor assembly, and the RF power source, wherein the controller is configured to: receive the measurement characterizing the cooking process from the sensor assembly, process the measurement to determine a modified cooking process, and operate the antenna assembly and the RF power source in accordance with the modified cooking process in real-time.

[0008] A further disclosure is US 2020 / 260529 A1 disclosing a computer-implemented method for heating an item in a chamber of an electronic oven towards a target state includes heating the item with a set of applications of energy to the chamber while the electronic oven is in a respective set of configurations. The set of applications of energy and respective set of configurations define a respective set of variable distributions of energy in the chamber. The method also includes sensing sensor data that defines a respective set of responses by the item to the set of applications of energy. The method also includes generating a plan to heat the item in the chamber. The plan is generated by a control system of the electronic oven and uses the sensor data.

[0009] A further disclosure is US 10 219 330 B2 disclosing an electronic oven and an accompanying control system that avoid boiling or splattering in a heating chamber of the oven while an item is being heated in the chamber. A disclosed method which can be executed by the control system includes evaluating sensor data from a visible light sensor and sensor data from an infrared light sensor. The controller is communicatively coupled to the visible light sensor and the infrared light sensor. The method also comprises generating a splatter prediction in response to the evaluation of the sensor data from the visible light sensor and the sensor data from the infrared light sensor. The method also comprises decreasing a power level of the microwave energy source in response to the splatter prediction. The controller is also communicatively coupled to the microwave energy source.

[0010] SUMMARY OF THE INVENTION

[0011] An object of the invention is to overcome one or more of the disadvantages mentioned above.

[0012] According to a first aspect of the invention, a heating system for heating an object, comprising: a chamber for holding the object; and an RF source arranged for radiating RF energy into the chamber for heating the object; wherein the RF source comprises: a frequency input for adapting a frequency of the radiated RF energy; and a magnitude input for adapting a magnitude of the radiated RF energy; wherein the heating system further comprises: a visual camera arranged for recording a visual pattern of the object; an infrared camera arranged for recording a heat pattern of the object; and a controller arranged for: retrieving a heating pattern for the object; receiving a recorded visual pattern; starting with low-power looping comprising: receiving a recorded low-power heat pattern; generating a frequency setting and a low-magnitude setting while adapting the frequency setting based on the recorded visual pattern and the recorded low-power heat pattern; transmitting the frequency setting and the low-magnitude setting to the frequency input and the magnitude input, respectively; and deciding to loop, to stop or to continue with high-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object; and continuing with high-power looping comprising: receiving a recorded heat pattern; generating with a high magnitude setting while maintaining the applicable frequency setting found during the low-power looping; transmitting the frequency setting and the high-magnitude setting to the frequency input and the magnitude input, respectively; and deciding to loop, to stop or to continue with low-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object.

[0013] The heating system is based on heating an object with RF energy, microwave energy, or radio frequency energy. The frequency range is typically from 300 MHz to 300 GHZ, preferably 1 GHz to 100 GHz. The heating is typically dielectric heating. The RF energy typically has a frequency, and an energy level or a magnitude used in a microwave oven. The heating system is suitable for drying, defrosting, thawing, cooking, pasteurising, sterilising, or tempering various objects made of a material or combination of materials, particularly sensitive to radio frequency (RF) heating, within a chamber or a cavity using an RF source or generator. The material sensitive to RF may be partly metallic in nature, such as a material doped with metal particles. The material sensitive to RF may be ceramic in nature. The material sensitive to RF may be dielectric and / or conductive for accepting RF energy. The material or combination of materials may be of an organic nature, such as a biological nature, or a non-organic nature, such as a metallic nature, plastic nature, epoxy nature, or carbon nature. The chamber is typically a closed chamber preventing the surroundings of the heating system to be heated by RF energy exiting or radiating from or out of the chamber.

[0014] The RF source comprises a frequency input and a magnitude input. The frequency input is for adapting a frequency of the radiated RF energy. The magnitude input is for adapting a magnitude, power or amount of the radiated RF energy. Adapting the frequency and the magnitude allow to change or adapt the distribution of the RF energy in the chamber, including to change or adapt the distribution of the RF energy in the object, and thereby change or adapt the heating of the object. The chamber or cavity is typically accommodating the adaptation of the RF energy. The adaptation of the RF energy is typically based on adapting the mode or modes of the RF energy. The chamber should be able to accommodate different modes of the RF energy for allowing adaptation of the RF energy distribution. Such a chamber may be typed as a multi-mode chamber.

[0015] The heating system further comprises a visual camera, and an infrared camera. The visual camera is arranged for recording a visual pattern of the object. The visual camera operates in the visual light spectrum, typically the light spectrum visible to the human eye. The infrared camera is arranged for recording a heat pattern of the object. The recorded pattern may be an image. The recorded pattern may be a processed image. The recorded pattern may be solely pattern information processed at or in the camera. The pattern information may comprise shape information. The pattern information may comprise object area, volume, and / or size information.

[0016] The heating system further comprises a controller. The controller is arranged for receiving a recorded visual pattern. The recorded visual pattern is received from the visual camera. The controller is further arranged for receiving a recorded heat pattern. The recorded heat pattern is received from the infrared camera.

[0017] The controller is further arranged for retrieving a heating pattern for the object. Retrieving may comprise retrieving a heating pattern or a temperature distribution information for the object, such as a load, by identifying the object and preprogramming or predefining the heating pattern, such as retrieving the heating pattern from a computer storage, e g. a disk or USB storage. Alternatively, retrieving may comprise reading a QR label, a barcode, a written instruction on the package of the object or load for therefrom deducing the heating pattern. The heating pattern may be to evenly heat the object, or evenly spread the heat through the object. The heating pattern may be to apply more heat to the inner parts, such as the core, of the object. The heating pattern may be to apply more heat to the outer parts, such as the crust or outer shell, of the object.

[0018] The controller may further be arranged for providing the recorded visual pattern and the recorded heat pattern to a trained neural network. The trained neural network is typically comprised or at least partly comprised by the controller. The trained neural network may be partly cloud-based. The trained neural network is trained for generating a frequency setting and a magnitude setting based on the recorded visual pattern and the recorded heat pattern. The trained neural network may comprise a trained neural network for recognizing a shape, area, volume, and / or size of the object in a visual pattern. The trained neural network may comprise a trained neural network for recognizing a shape, area, volume, and / or size of the object in the heat pattern. The trained neural network typically combines the recorded visual pattern and the recorded heat pattern. Alternatively, the recorded visual pattern and the recorded heat pattern are combined before the combination of the information is provided to the trained neural network. The trained neural network is trained for as quickly as possible obtaining the heating pattern in the object. The trained neural network may be trained for as quickly as possible evenly heating the object. The trained neural network is therefore trained balancing obtaining the heating pattern in the object and quickness of the heating of the object. The quicker the object is heated, the less heat is spread based on the conduction of the heat through the object, and thus the more influence the adaptation of the RF energy radiated into the chamber has.

[0019] An issue identified by the inventor is that the presence of the object in the chamber or cavity distorts or disturbs the RF energy spreading in the chamber or cavity. The distortion or disturbance of the RF energy may be caused by uneven object permittivity distribution, object geometrical effects. The distortion or disturbance of the RF energy may be caused by presence in the chamber of a heat sink, such as a cold plate underneath the object. The distortion or disturbance of the RF energy results in RF energy heating specific parts of the object more compared to other parts of the object. The distortion or disturbance is almost always unequal to the heating pattern. An insight is that to obtain the heating pattern inside the object, the RF energy is to be adapted. Further, if the heating pattern is a pattern of evenly spreading the energy or temperature, the unevenly spread RF energy is to be spread through the object by conduction, which is slow or taking quite some time. Furthermore, energy conduction also conducts to other parts, such as to parts of the chamber or even to outside the chamber causing loss of RF energy and thus energy inefficiency.

[0020] The trained neural network may map the recorded visual pattern and the recorded heat pattern for determining an object heat pattern. The trained neural network may determine or adapt the frequency and / or the magnitude of the RF energy based on the object heat pattern. Typically, the trained neural network is fed with the information from the subtraction of a second recorded heat pattern taken after the application of the RF energy and a first recorded heat pattern taken before the application of the RF energy. The trained neural network generates a frequency setting and a magnitude setting based on the recorded visual pattern and the recorded heat pattern. The trained neural network may be fed with time information for basing the generated frequency setting and the generated magnitude setting also on heat conduction overtime. The trained neural network is trained to provide the technical effect that the generated frequency and magnitude settings improve obtaining the heating pattern in the object while also shortening the time for heating the object. Furthermore, the trained neural network is trained to provide the RF energy directly to the right, correct, or requested location, providing the technical effect of obtaining the heating pattern more efficiently, thus less RF energy is used for obtaining the heating pattern. Furthermore, as the RF energy distribution in the object is adaptable, the object may be arranged stationary in the chamber obviating any mechanical parts changing the position and / or orientation, such as rotating, of the object inside the chamber during heating.

[0021] According to another aspect of the invention, a method for heating an object in a chamber, comprising: retrieving a heating pattern for the object; receiving a recorded visual pattern of the chamber; starting with low-power looping comprising: receiving a recorded low-power heat pattern of the chamber; retrieving a heating pattern for the object; generating a frequency setting and a low-magnitude setting while adapting the frequency setting for an RF source based on the recorded visual pattern and the recorded heat pattern using a trained neural network, wherein the RF source is arranged for radiating RF energy into the chamber for heating the object; and transmitting the frequency setting and the low-magnitude setting to the RF source for adapting a frequency of the radiated RF energy, and for adapting a magnitude of the radiated RF energy, respectively; deciding to loop, to stop or to continue with high-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object; and continuing with high-power looping comprising: receiving a recorded heat pattern; generating with a high magnitude setting while maintaining the applicable frequency setting found during the low-power looping; transmitting the frequency setting and the high-magnitude setting to the RF source for adapting the frequency of the radiated RF energy, and for adapting the magnitude of the radiated RF energy, respectively; and deciding to loop, to stop or to continue with low-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object wherein the trained neural network is trained for adapting the RF energy distribution for obtaining the heating pattern in the object.

[0022] In an embodiment of the method, the method comprises: receiving a second recorded visual pattern; and receiving a second recorded heat pattern; wherein generating comprises generating a second frequency setting and a second magnitude setting, and a second phase setting; and wherein the method further comprises transmitting the second frequency setting, the second magnitude setting, and the second phase setting to the frequency second input, the second magnitude input, and the second phase input, respectively. The second phase input provides the advantage of improving, typically greatly improving, the adaptability of the RF energy distribution inside the chamber. According to another aspect of the invention, a computer program product comprising instructions which, when the program is executed by a suitable processor, cause the processor to carry out any of the method embodiments. The computer program product provides the same advantages as mentioned for the heating system or method.

[0023] According to another aspect of the invention, a neural network trainer for generating a trained neural network for heating system according to any of the embodiments, wherein the neural network trainer comprises: a cloud coupling for coupling to a plurality of heating systems and arranged for: receiving a recorded visual pattern from a heating system of the plurality of heating systems; receiving a recorded heat pattern from the heating system; receiving a heating pattern for the object from the heating system; receiving a generated frequency setting and a generated magnitude setting from the heating system; and transmitting to the heating system settings for the trained neural network, preferably weights for nodes of the trained neural network; and a generator arranged for: retrieving a neural network, preferably a trained neural network; training the neural network based on the recorded visual pattern, the recorded heat pattern, the generated frequency setting, and the generated magnitude setting; and providing the settings of the newly trained neural network to the cloud coupling.

[0024] The neural network trainer provides or enables the same advantages as mentioned for the heating system, or improves the advantages as mentioned for the heating system.

[0025] According to another aspect of the invention, a heating system for heating an object, comprising: a chamber for holding the object; and an RF source arranged for radiating RF energy into the chamber for heating the object; wherein the RF source comprises: a frequency input for adapting a frequency of the radiated RF energy; and a magnitude input for adapting a magnitude of the radiated RF energy; wherein the heating system further comprises: a visual camera arranged for recording a visual pattern of the object; an infrared camera arranged for recording a heat pattern of the object; and a controller arranged for: retrieving a heating pattern for the object; low-power looping with a low-power magnitude setting comprising: receiving a recorded visual pattern; receiving a recorded heat pattern; deciding on low-power looping based on comparing the recorded heat pattern with the heating pattern, wherein if the comparison is below an exit threshold, the low-power loop is exited, and wherein if a similarity between the recorded heat pattern and the heating pattern is below a similarity threshold, the controller continues with a high-power looping; generating a frequency setting and a low-power magnitude setting based on the recorded visual pattern and the recorded heat pattern using a neural network; and transmitting the frequency setting and the magnitude setting to the frequency input and the magnitude input, respectively; the high-power looping with a high-power magnitude setting comprising: receiving a recorded visual pattern; receiving a recorded heat pattern; deciding on high-power looping based on comparing the recorded heat pattern with the heating pattern, wherein if the comparison is below an exit threshold, the high-power loop is exited, and wherein if a similarity between the recorded heat pattern and the heating pattern is above a similarity threshold, the controller continues with the low-power looping; generating a frequency setting and a high-power magnitude setting based on the recorded visual pattern and the recorded heat pattern using a neural network; and transmitting the frequency setting and the magnitude setting to the frequency input and the magnitude input, respectively; and wherein the neural network is trained for adapting the RF energy distribution for obtaining the heating pattern in the object. This aspect of the invention provides the same advantages as mentioned for the other embodiments and aspects of the invention. Furthermore, this aspect of the invention stipulates that the neural network may be self-training based on the feedback loop, specifically the low-power loop, and heating pattern provided for the object. This self-training provides the further advantage that the heating system adapts to heating particular or specific objects repetitively, such as heating dough of a bread roll on a production line in a factory. Furthermore, self-training may start without a trained neural network. This aspect of the invention may be combined with other features of other embodiments for obtaining the advantages specified for that embodiment, or even improving that advantage.

[0026] DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS

[0027] In an embodiment of the heating system, the visual camera and the infrared camera are arranged next to each other. The visual camera and the infrared camera thereby have substantially the same view of or substantially the same perspective on, preferably the same view of or the same perspective on, the chamber and the object. The correlation between the recorded visual pattern and the recorded heat pattern is easier, which translates in shortening the training of the neural network, and / or improved trained neural network. The improved trained neural network advantageously provides settings for the RF source, which result in faster heating and / or reproduce the heating pattern better in the object.

[0028] In an embodiment of the heating system, the heating pattern is evenly heating the object, preferably to a specific temperature. When the heating pattern is evenly spreading the heat over the object or part of the object, such as an item of the object, the evenness may be defined as the maximum temperature minus the minimum temperature divided by the average temperature. Other definitions such as involving a standard deviation may be applied. When the heating pattern is not evenly spreading the heat over the object or part of the object, such as an item of the object, the conformity to the heating pattern may be defined as the summation of the difference between the actual temperature and the intended temperature for all pixels divided by the number of pixels. Compliance with the heating pattern is typically measured by applying one of the above measures and comparing this measurement with a threshold, typically predefined threshold.

[0029] In an embodiment of the heating system, the object comprises several items; and the heating pattern comprises heating patterns for each item of the several items. Heating individual items of the object provides the advantage of control over the temperature rise is in the different items by controlling the RF energy distribution. The object may be a plate holding a diner with different types of food. The RF distribution is then preferably such that the plate is receiving less RF energy while the food is receiving more RF energy. Furthermore, if the food comprises meat, vegetables and potatoes, the RF energy distribution may be such that the potatoes receive more RF energy compared to the vegetables, and both are receiving RF energy evenly. The RF energy distribution for the meat might be to first heat the outer layer for keeping the fluids of the meat inside and thereafter heat the inside of the meat. This embodiment provides the advantage of a more targeted heating of the object comprising several items. In a preferred embodiment, the heating pattern for each item is evenly heating the item. In a preferred embodiment, the heating pattern for each item is heating the item to a specific temperature. Referring to the food example, not overcooking the meat while still cooking the potatoes enough or through and through.

[0030] In an embodiment, the heating system comprises a second visual camera arranged for recording a second visual pattern of the object; wherein the controller is further arranged for: receiving a second recorded visual pattern; and generating is also based on the second recorded visual pattern. This embodiment provides the advantage of improving the visual information of the object inputted in the trained neural network for obtaining improved settings for the RF source for subsequently obtaining improved compliance of the heated object to the heating pattern which is set.

[0031] In an embodiment of the heating system, the visual camera and the second visual camera are arranged such that a combination of the recorded visual pattern and the second recorded visual pattern provide object volume size information; generating comprises deducing the object volume size information; and the frequency setting and the magnitude setting are also based on the object volume size information. The second recorded visual pattern provides the advantage of allowing to estimate the volume of the object, and / or improved shape recognition of the object. Volume or shape typically give an indication of the mass of the object. Mass of the object translates to an amount of RF energy to heat the object to a specific temperature of heating pattern. Although the trained neural network may not be trained to estimate the mass, but may be trained to translate the inputted visual patterns to settings for the RF source, preferably influencing the magnitude setting. In a preferred embodiment, the second visual camera is arranged relative to the visual camera with a different view or perspective on the object, preferably a substantial view or perspective on the object, such as viewing the object in the chamber from different walls of the chamber.

[0032] In an embodiment, the heating system comprises a second infrared camera arranged for recording a second infrared pattern of the object; wherein the controller is further arranged for: receiving a second recorded infrared pattern; and generating is also based on the second recorded infrared pattern. This embodiment provides the advantage of improving the infrared information of the object inputted in the trained neural network for obtaining improved settings for the RF source for subsequently obtaining improved compliance of the heated object to the heating pattern which is set.

[0033] In an embodiment of the heating system, the infrared camera and the second infrared camera are arranged such that a combination of the recorded infrared pattern and the second recorded infrared pattern provide object volume heat information; generating comprises deducing the object volume heat information; and the frequency setting and the magnitude setting are also based on the object volume heat information. The second recorded infrared pattern provides the advantage of allowing to estimate the heat volume of the object, and / or improved heat shape recognition of the object. Heat volume or heat shape typically give an indication of the mass of the object. Mass of the object translates to an amount of RF energy to heat the object to a specific temperature of heating pattern. Although the trained neural network may not be trained to estimate the mass, but may be trained to translate the inputted infrared patterns to settings for the RF source, preferably influencing the magnitude setting. In a preferred embodiment, the second infrared camera is arranged relative to the infrared camera with a different view or perspective on the object, preferably a substantial view or perspective on the object, such as viewing the object in the chamber from different walls of the chamber.

[0034] In an embodiment, the heating system comprises a second visual camera and a second infrared camera for providing the combined advantage as mentioned above for improved accuracy of the settings for the RF source generated by the trained neural network. In a preferred embodiment the cameras and the second cameras are arranged in pairs, wherein a pair is an infrared camera arranged next to a visual camera. For even further improving the accuracy of the settings for the RF source generated by the trained neural network. In an embodiment of the heating system, receiving a recorded visual pattern comprises receiving a recorded visual pattern before the object is present in the chamber. Subtracting a recorded visual pattern without the object from a recorded visual pattern with the object allows to better estimate and / or determine a size, a shape, and / or a volume of the object. Both patterns may be provided to the trained neural network or alternatively be part of the preprocessing of the information provided to the trained neural network.

[0035] In an embodiment of the heating system, receiving a recorded infrared pattern comprises receiving a recorded infrared pattern before the object is present in the chamber. Subtracting a recorded infrared pattern without the object from a recorded infrared pattern with the object allows to better estimate and / or determine a size, a shape, and / or a volume of the heat of the object. Both patterns may be provided to the trained neural network or alternatively be part of the preprocessing of the information provided to the trained neural network. In a preferred embodiment, receiving comprises receiving a recorded visual pattern and receiving a recorded infrared pattern both before the object is present in the chamber for enhancing the advantages as mentioned for the individual features even more.

[0036] In an embodiment of the heating system, the controller is arranged for real-time controlling the frequency setting and the magnitude setting during heating the object. Controlling during the heating of the object advantageously allows to adapt the RF source during heating for as well as possible providing the heating pattern in the object. As an example, heating food such as defrosting or thawing food causes ice in parts of the food to turn into water. In general, ice is typically transparent or nearly transparent to RF energy while water is absorbing RF energy. This effect may result in parts of the food being cooked while other parts are not defrosted. This uneven spreading of the heat is typically unwanted and can advantageously be countered with realtime adapting the RF source for providing the RF energy at locations or parts in the object needing the most RF energy to comply to the heating pattern.

[0037] In an embodiment, the heating system comprises a second RF source; wherein the second RF source comprises: a second frequency input for adapting a frequency of the radiated RF energy; a second magnitude input for adapting a magnitude of the radiated RF energy; and a second phase input for adapting the phase of the radiated RF energy relative to the radiated RF energy of the RF source; wherein the controller is further arranged for: receiving a second recorded visual pattern; and receiving a second recorded heat pattern; wherein generating comprises generating a second frequency setting and a second magnitude setting, and a second phase setting also based on the second recorded visual pattern and the second recorded heat pattern; and wherein the controller is further arranged for transmitting the second frequency setting, the second magnitude setting, and the second phase setting to the frequency second input, the magnitude input, and the second phase input, respectively. A second RF source advantageously allows to introduce another RF energy distribution in the chamber for heating the object such that the heating pattern is obtained. The second RF source comprising a second phase input allows the RF source and the second RF source to synchronise their radiated RF energy for advantageously further adapting the RF energy distribution in the chamber for heating the object such that the heating pattern is obtained.

[0038] In an embodiment of the heating system, the controller is further arranged for low power looping: the generating of RF energy with a low magnitude setting while adapting the frequency setting; the receiving a recorded heat pattern; and deciding to stop low power looping based on comparing the recorded heat pattern with the heating pattern for the object; and the controller is further arranged for high power looping: the generating with a high magnitude setting while maintaining the applicable frequency setting found during the low power looping; the receiving a recorded heat pattern; and deciding to stop high power looping based on comparing the recorded heat pattern with the heating pattern for the object. First low power looping before high power loping allows to first measure the effect of the adaptation of the RF source and thus the RF energy radiated into the chamber for thereafter efficiently applying high power loping for advantageously obtaining quickly and / or efficiently obtaining the heating pattern in the heated object. Furthermore, the low power looping allows for the neural network to train itself for improving the generating of the settings by the improved trained neural network.

[0039] In an embodiment of the heating system, the RF source is an RF solid state source. The RF solid state source provides the advantage of being highly reproduceable. The RF energy distribution in the chamber may vary considerably when the frequency of the radiated RF energy slightly changes or varies. Applying an RF solid state source therefore greatly improves the reproducibility of the RF energy distribution. This advantage may be even more enhanced when multiple RF sources, such as a second RF source, are radiating RF energy into the chamber. This advantage may even be more enhanced when these multiple RF sources, such as a second RF source, comprise a phase input for adapting the phase of the radiated RF energy relative to the radiated RF energy of the other RF source.

[0040] In an embodiment, the heating system comprises a cloud coupling for coupling to a neural network trainer; wherein the controller is further arranged for: transmitting the recorded visual pattern to the neural network trainer; transmitting the recorded heat pattern to the neural network trainer; transmitting the heating pattern for the object to the neural network trainer; transmitting the generated frequency setting and the generated magnitude setting to the neural network trainer; and receiving from the neural network trainer settings for the trained neural network, preferably weights for nodes of the trained neural network. The trained neural network may advantageously improve with the measurement and knowledge of the heating system.

[0041] In this embodiment, the trained neural network is not only trained or improved with the measurement and knowledge of the heating system, but also of other heating system. In this embodiment, to prevent training the neural network at multiple locations and to prevent excessive data exchange, the neural network is trained externally, whereafter a new trained neural network is obtained via the cloud coupling for improved working of the heating system.

[0042] BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The invention will be apparent from and elucidated further with reference to the embodiments described by way of example in the following description and with reference to the accompanying drawings, in which:

[0044] Figure 1 schematically shows a heating system;

[0045] Figure 2 schematically shows simulation results of a detail of a heating system;

[0046] Figure 3 schematically shows simulation results of a heating system;

[0047] Figure 4 schematically shows a method for the heating system;

[0048] Figure 5 schematically shows a method for the heating system;

[0049] Figure 6 schematically shows an embodiment of a computer program product, computer readable medium and / or non-transitory computer readable storage medium according to the invention.

[0050] The figures are purely diagrammatic and not drawn to scale. In the figures, elements which correspond to elements already described may have the same reference numerals.

[0051] LIST OF REFERENCE NUMERALS

[0052] DETAILED DESCRIPTION OF THE FIGURES

[0053] The following figures may detail different embodiments. Embodiments can be combined to reach an enhanced or improved technical effect. These combined embodiments may be mentioned explicitly throughout the text, may be hinted upon in the text or may be implicit.

[0054] Figure 1 schematically shows a heating system 100. The heating system is arranged for heating an object 10. The heating system comprises: a chamber 110, an RF source 120, a visual camera 130, an infrared camera 140, and a controller 150. The object, although shown as a cuboid, may represent meat arranged at the bottom in the chamber in this example. The infrared camera and the visual camera are arranged to the top of the chamber facing downward on the object. The RF source comprises a frequency input 121 , and a magnitude input 122.

[0055] The heating system may comprise a second RF source 125 for introducing RF energy into the chamber for heating the object. The second RF source comprises a second frequency input 126, and a second magnitude input 127. The second frequency and magnitude inputs provide the advantage of improved adaptation of the RF energy distribution. The second RF source may comprise a second phase input 128. The second phase input allows to synchronise the RF source and the second RF source for even further improving adaptability of the RF energy distribution.

[0056] Figure 2 schematically shows simulation results of a detail of a heating system 100. For clarity only the RF energy distribution 123 for the object is shown and not for the space outside the object but inside the chamber.

[0057] The simulation is performed for an object being or mimicking raw beef or meat loaf according to IEC 60705 tests. The object has the size of 100x225x45 mm. The simulation assumes dielectric properties for space in the chamber at room temperature and the object at-20 degrees Celsius. The dielectric properties for space in the chamber are = 52.4, tan(6Rr)=0.33, and for the object are 4.4, tan(6Rr)=0.12.

[0058] Figure 3 schematically shows simulation results of a heating system 100. A single RF source is present in the heating system. In this simulation, no object in the chamber is shown and thus taken into account in the simulation.

[0059] A three-dimensional axis is shown in the simulation results. The three-dimensional axis is labelled only for the left top simulation. The origin of the axis are in the centre of the bottom of the chamber. The X axis is directed from the origin to the right top. The Z axis is directed from the origin to the right bottom. The Y axis is directed upwards.

[0060] The simulation results or RF distributions are shown only for three distinct planes all having the origin in their plane. The XY plane goes through the X axis and the Y axis. The XZ plane goes through the X axis and the Z axis. The YZ plane goes through the Y axis and the Z axis.

[0061] A first simulation shown on the left top is performed at 2400 MHZ. A second simulation shown on the right top is performed at 2415 MHZ. A third simulation shown on the left bottom is performed at 2416 MHZ. A fourth simulation shown on the right bottom is performed at 2433 MHZ. The difference of the RF distribution between the second and third simulation is minimal, while the change in frequency is minimal. This show that the frequency may have a small variation while still providing a reproduceable resulting RF distribution. Further, the differences between the first and second simulations, and the third and fourth simulations show a considerable RF energy distribution change. Hot spots are adaptable in the sense of their location as well as the magnitude difference between the hot spot and the surrounding space in the chamber. These simulations show the particular advantage of applying a solid state RF sources due to the reproducibility, more so the very reproducibility, of the frequency of the radiated RF energy resulting in a very reproducible RF energy distributions inside the chamber.

[0062] Figure 4 schematically shows a method 200 for the heating system 100. The method is arranged for heating an object in a chamber. The method comprises: receiving 210 a recorded visual pattern, receiving 220 a recorded heat, retrieving 230 a heating pattern, generating 240 a frequency setting and a magnitude setting, and transmitting 250 settings. The receiving the recorded visual pattern, the receiving the recorded heat pattern, and the retrieving the heating pattern for the object may be done in arbitrary order and / or in parallel. Receiving a recorded visual and / or infrared pattern may be done multiple times. Before generating settings, receiving a recorded visual and an infrared pattern should be done at least once. Generating settings may be done multiple times, typically for each set of received recorded visual and infrared pattern. Transmitting settings is typically done after each time new settings are generated.

[0063] The receiving is of a recorded visual pattern of the chamber. The receiving is of a recorded heat pattern of the chamber. The retrieving is of a heating pattern for the object. The generating is of a frequency setting and a magnitude setting for an RF source based on the recorded visual pattern and the recorded heat pattern using a trained neural network, wherein the RF source is arranged for radiating RF energy into the chamber for heating the object. The transmitting is of the frequency setting and the magnitude setting to the RF source for adapting a frequency of the radiated RF energy, and for adapting a magnitude of the radiated RF energy, respectively. The trained neural network is trained for adapting the RF energy distribution for obtaining the heating pattern in the object.

[0064] Figure 5 schematically shows a method 300 for heating an object in a chamber. The method comprises a low- power loop 301 and a high-power loop 302. The method start 303 with retrieving 330 a heating pattern. After retrieving the low-power loop starts with receiving 310, 320 recorded visual and infrared patterns. After receiving the respective patterns, the received patterns are compared with the retrieved heating pattern. If the heating pattern is present in the object in the chamber, the low-power loop is exited 370. If the heating pattern is not yet present, but the heating pattern is similar enough to the heating pattern, a decision may be taken to continue 365 with the high-power loop. Otherwise, next is to generate 340 settings for the RF source taken into account a low- power setting for the magnitude. Generating is followed by transmitting 350 the generated settings to the RF source for the settings to take effect. After transmitting the settings, the low-power loop loops back to receiving recorded visual and infrared patterns.

[0065] The high-power loop is entered from the low-power loop by generating 341 settings for the RF source taken into account a high power setting for the magnitude. Generating is followed by transmitting 351 the generated settings to the RF source for the settings to take effect. After transmitting the settings, the high-power loop loops back to receiving 311 , 321 recorded visual and infrared patterns. After receiving the respective patterns, the received patterns are compared with the retrieved heating pattern. If the heating pattern is present in the object in the chamber, the high-power loop is exited 370’. If the heating pattern is not yet present, and the heating pattern is deviating too much or starts to deviate too much from the heating pattern, a decision may be taken to continue with the low-power loop 366. If the heating pattern is not yet present, but the heating pattern is similar enough to the heating pattern, a decision may be taken to continue with the high-power loop by generating 341 settings for the RF source taking into account a high-power setting for the magnitude. Generating is followed by transmitting 351 the generated settings to the RF source for the settings to take effect. After transmitting the settings, the high-power loop loops back to receiving recorded visual and infrared patterns.

[0066] The disclosed method provides the advantage of only applying high-power when the heating of the object is going in the direction of the heating pattern. The disclosed method therefore advantageously prevents to fast deviate from the heating pattern preventing overheating, such as local overheating.

[0067] Figure 6 schematically shows an embodiment of a computer program product 1000, computer readable medium 1010 and / or non-transitory computer readable storage medium comprising computer readable code 1020 according to the invention. The video recording assembly may comprise a part, such as the carrier frame, arranged on a user. The video recording assembly may comprise another part, not arranged on a user. The part not arranged on the user typically may comprise a processing unit for processing the video stream from the video recording assembly. The part not arranged on the user may be typed as an external part, server and / or smartbox. In another embodiments, the video processing unit may be arranged to the carrier frame.

[0068] It will also be clear that the above description and drawings are included to illustrate some embodiments of the invention, and not to limit the scope of protection. Starting from this disclosure, many more embodiments will be evident to a skilled person without departing from the scope of the invention as set forth in the appended claims. These embodiments are within the scope of protection and the essence of this invention and are obvious combinations of prior art techniques and the disclosure of this patent. Devices functionally forming separate devices may be integrated in a single physical device.

[0069] The term “substantially” herein, such as in “substantially all emission" or in “substantially consists", will be understood by the person skilled in the art. The term “substantially" may also include embodiments with “entirely", “completely", “all", etc. Hence, in embodiments the adjective substantially may also be removed. Where applicable, the term “substantially" may also relate to 90% or higher, such as 95% or higher, especially 99% or higher, even more especially 99.5% or higher, including 100%. The term “comprise" also includes embodiments wherein the term “comprises" means “consists of’.

[0070] The term "functionally" will be understood by, and be clear to, a person skilled in the art. The term “substantially" as well as “functionally" may also include embodiments with “entirely", “completely", “all", etc. Hence, in embodiments the adjective functionally may also be removed. When used, for instance in “functionally parallel", a skilled person will understand that the adjective “functionally" includes the term substantially as explained above. Functionally in particular is to be understood to include a configuration of features that allows these features to function as if the adjective “functionally" was not present. The term “functionally" is intended to cover variations in the feature to which it refers, and which variations are such that in the functional use of the feature, possibly in combination with other features it relates to in the invention, that combination of features is able to operate or function. For instance, if an antenna is functionally coupled or functionally connected to a communication device, received electromagnetic signals that are received by the antenna can be used by the communication device. The word “functionally" as for instance used in “functionally parallel" is used to cover exactly parallel, but also the embodiments that are covered by the word “substantially" explained above. For instance, “functionally parallel" relates to embodiments that in operation function as if the parts are for instance parallel. This covers embodiments for which it is clear to a skilled person that it operates within its intended field of use as if it were parallel.

[0071] Furthermore, the terms first, second, third and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances and that the embodiments of the invention described herein are capable of operation in other sequences than described or illustrated herein. Thus, these terms are not necessarily intended to indicate temporal or other prioritization of such elements.

[0072] The devices or apparatus herein are amongst others described during operation. As will be clear to the person skilled in the art, the invention is not limited to methods of operation or devices in operation.

[0073] It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. Use of the verb "to comprise" and “to include", and its conjugations does not exclude the presence of elements or steps other than those stated in a claim. Also, the use of introductory phrases such as “at least one" and “one or more" in the claims should not be construed to imply that the introduction of another claim element by the indefinite articles "a" or "an" limits any particular claim containing such introduced claim element to inventions containing only one such element, even when the same claim includes the introductory phrases "one or more" or "at least one" and indefinite articles such as "a" or "an." The article "a" or "an" preceding an element does not exclude the presence of a plurality of such elements.

[0074] The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the device or apparatus claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

[0075] The invention further applies to an apparatus or device comprising one or more of the characterising features described in the description and / or shown in the attached drawings. The invention further pertains to a method or process comprising one or more of the characterising features described in the description and / or shown in the attached drawings.

[0076] It will be appreciated that the invention also applies to computer programs, particularly computer programs on or in a carrier, adapted to put the invention into practice. The program may be in the form of a source code, a code intermediate source and an object code such as in a partially compiled form, or in any other form suitable for use in the implementation of the method according to the invention. It will also be appreciated that such a program may have many different architectural designs. For example, a program code implementing the functionality of the method or system according to the invention may be sub-divided into one or more sub-routines. Many different ways of distributing the functionality among these sub-routines will be apparent to the skilled person. The sub-routines may be stored together in one executable file to form a self-contained program. Such an executable file may comprise computer-executable instructions, for example, processor instructions and / or interpreter instructions (e g. Java interpreter instructions). Alternatively, one or more or all of the sub-routines may be stored in at least one external library file and linked with a main program either statically or dynamically, e g. at run-time. The main program contains at least one call to at least one of the sub-routines. The sub-routines may also comprise function calls to each other. An embodiment relating to a computer program product comprises computer-executable instructions corresponding to each processing stage of at least one of the methods set forth herein. These instructions may be sub-divided into sub-routines and / or stored in one or more files that may be linked statically or dynamically. Another embodiment relating to a computer program product comprises computerexecutable instructions corresponding to each means of at least one of the systems and / or products set forth herein. These instructions may be sub-divided into sub-routines and / or stored in one or more files that may be linked statically or dynamically.

[0077] The carrier of a computer program may be any entity or device capable of carrying the program. For example, the carrier may include a data storage, such as a ROM, for example, a CD ROM or a semiconductor ROM, or a magnetic recording medium, for example, a hard disk. Furthermore, the carrier may be a transmissible carrier such as an electric or optical signal, which may be conveyed via electric or optical cable or by radio or other means. When the program is embodied in such a signal, the carrier may be constituted by such a cable or other device or means. Alternatively, the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being adapted to perform, or used in the performance of, the relevant method.

[0078] The various aspects discussed in this patent can be combined in order to provide additional advantages. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage. Furthermore, some of the features can form the basis for one or more divisional applications.

[0079] Furthermore, the methods mentioned may be implementable and executable on a computer.

Claims

CLAIMS1. Heating system (100) for heating an object (10), comprising:- a chamber (110) for holding the object; and- an RF source (120) arranged for radiating RF energy into the chamber for heating the object; wherein the RF source comprises:- a frequency input (121) for adapting a frequency of the radiated RF energy; and- a magnitude input (122) for adapting a magnitude of the radiated RF energy; wherein the heating system further comprises:- a visual camera (130) arranged for recording a visual pattern of the object;- an infrared camera (140) arranged for recording a heat pattern of the object; and- a controller (150) arranged for: retrieving (230) a heating pattern for the object; receiving (210) a recorded visual pattern; starting with low-power looping comprising: receiving (220) a recorded low-power heat pattern; generating (240) a frequency setting and a low-magnitude setting while adapting the frequency setting based on the recorded visual pattern and the recorded low-power heat pattern; transmitting (250) the frequency setting and the low-magnitude setting to the frequency input and the magnitude input, respectively; and deciding to loop, to stop or to continue with high-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object; and continuing with high-power looping comprising: receiving a recorded heat pattern; generating with a high magnitude setting while maintaining the applicable frequency setting found during the low-power looping; transmitting the frequency setting and the high-magnitude setting to the frequency input and the magnitude input, respectively; and deciding to loop, to stop or to continue with low-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object.

2. Heating system according to the preceding claim, wherein the visual camera and the infrared camera are arranged next to each other.

3. Heating system according to any of the preceding claims, wherein the low-power looping comprises receiving (210) a recorded visual pattern; and / or wherein the high-power looping comprises receiving a recorded visual pattern.

4. Heating system according to any of the preceding claims, wherein the generating (240) the frequency setting and the low-magnitude setting uses a trained neural network trained for adapting the RF energy distribution for obtaining the heating pattern in the object.

5. Heating system according to any of the preceding claims 1-3, wherein the generating (240) the frequency setting and the low-magnitude setting uses a limited list of frequency settings and magnitude settings, preferably not using a trained neural network.

6. Heating system according to any of the preceding claims 1-3, wherein the generating (240) the frequency setting and the low-magnitude setting uses an expert system for selecting a frequency setting and a magnitude setting, preferably not using a trained neural network.

7. Heating system according to any of the preceding claims, wherein the deciding for the high-power and / or low-power loop uses a trained neural network.

8. Heating system according to any of the preceding claims 1-6, wherein the deciding for the high-power and / or low-power loop uses a limited list of frequency settings and magnitude settings, preferably not using a trained neural network.

9. Heating system according to any of the preceding claims 1-6, wherein the deciding for the high-power and / or low-power loop uses an expert system for selecting a frequency setting and a magnitude setting, preferably not using a trained neural network.

10. Heating system according to any of the preceding claims, wherein the heating pattern is evenly heating the object, preferably to a specific temperature.

11. Heating system according to any of the preceding claims 1-9, wherein the object comprises several items; wherein the heating pattern comprises heating patterns for each item of the several items; wherein preferably the heating pattern for each item is evenly heating the item; and wherein preferably the heating pattern for each item is heating the item to a specific temperature.

12. Heating system according to any of the preceding claims, comprising a second visual camera arranged for recording a second visual pattern of the object; wherein the controller is further arranged for: receiving a second recorded visual pattern; and generating is also based on the second recorded visual pattern.

13. Heating system according to the preceding claim, wherein the visual camera and the second visual camera are arranged such that a combination of the recorded visual pattern and the second recorded visual pattern provide object volume size information; wherein generating comprises deducing the object volume size information; and wherein the frequency setting and the magnitude setting are also based on the object volume size information.

14. Heating system according to any of the preceding claims, comprising a second infrared camera arranged for recording a second infrared pattern of the object; wherein the controller is further arranged for: receiving a second recorded infrared pattern; and generating is also based on the second recorded infrared pattern.

15. Heating system according to the preceding claim, wherein the infrared camera and the second infrared camera are arranged such that a combination of the recorded infrared pattern and the second recorded infrared pattern provide object volume heat information; wherein generating comprises deducing the object volume heat information; and wherein the frequency setting and the magnitude setting are also based on the object volume heat information.

16. Heating system according to the preceding claims 13 and 15.

17. Heating system according to any of the preceding claims, wherein receiving a recorded visual pattern comprises receiving a recorded visual pattern before the object is present in the chamber; and / or wherein receiving a recorded infrared pattern comprises receiving a recorded infrared pattern before the object is present in the chamber.

18. Heating system according to any of the preceding claims, wherein the controller is arranged for real-time controlling the frequency setting and the magnitude setting during heating the object.

19. Heating system according to any of the preceding claims, comprising a second RF source; wherein the second RF source (125) comprises:- a second frequency input for adapting a frequency of the radiated RF energy;- a second magnitude input for adapting a magnitude of the radiated RF energy; and- a second phase input for adapting the phase of the radiated RF energy relative to the radiated RF energy of the RF source; wherein the controller is further arranged for: receiving a second recorded visual pattern; and receiving a second recorded heat pattern; wherein generating comprises generating a second frequency setting and a second magnitude setting, and a second phase setting also based on the second recorded visual pattern and the second recorded heat pattern; and wherein the controller is further arranged for transmitting the second frequency setting, the second magnitude setting, and the second phase setting to the frequency second input, the magnitude input, and the second phase input, respectively.

20. Heating system according to any of the preceding claims, wherein the controller is further arranged for low power looping: the generating with a low magnitude setting while adapting the frequency setting; the receiving a recorded heat pattern; and deciding to stop low power looping based on comparing the recorded heat pattern with the heating pattern for the object; and wherein the controller is further arranged for high power looping: the generating with a high magnitude setting while maintaining the applicable frequency setting found during the low power looping; the receiving a recorded heat pattern; and deciding to stop high power looping based on comparing the recorded heat pattern with the heating pattern for the object.

21. Heating system according to any of the preceding claims, wherein the RF source is a RF solid state source.

22. Heating system according to any of the preceding claims, comprising a cloud coupling for coupling to a neural network trainer; wherein the controller is further arranged for: transmitting the recorded visual pattern to the neural network trainer; transmitting the recorded heat pattern to the neural network trainer; transmitting the heating pattern for the object to the neural network trainer; transmitting the generated frequency setting and the generated magnitude setting to the neural network trainer; and receiving from the neural network trainer settings for the trained neural network, preferably weights for nodes of the trained neural network.

23. Method (200) for heating an object in a chamber, comprising:- retrieving (230) a heating pattern for the object;- receiving (210) a recorded visual pattern of the chamber;- starting with low-power looping comprising:- receiving (220) a recorded low-power heat pattern of the chamber;- generating (240) a frequency setting and a low-magnitude setting while adapting the frequency setting for an RF source based on the recorded visual pattern and the recorded heat pattern, wherein the RF source is arranged for radiating RF energy into the chamber for heating the object; and- transmitting (250) the frequency setting and the low-magnitude setting to the RF source for adapting a frequency of the radiated RF energy, and for adapting a magnitude of the radiated RF energy, respectively;- deciding to loop, to stop or to continue with high-power looping based on the recorded visual pattern andcomparing the recorded heat pattern with the heating pattern for the object; and- continuing with high-power looping comprising:- receiving a recorded heat pattern;- generating with a high magnitude setting while maintaining the applicable frequency setting found during the low-power looping;- transmitting the frequency setting and the high-magnitude setting to the RF source for adapting the frequency of the radiated RF energy, and for adapting the magnitude of the radiated RF energy, respectively; and- deciding to loop, to stop or to continue with low-power looping based on the recorded visual pattern and comparing the recorded heat pattern with the heating pattern for the object.

24. Method according to the preceding claim, comprising:- receiving a second recorded visual pattern; and- receiving a second recorded heat pattern; wherein generating comprises generating a second frequency setting and a second magnitude setting, and a second phase setting; and wherein the method further comprises transmitting in the low-power loop, and / or in the high-power loop the second frequency setting, the second magnitude setting, and the second phase setting to the frequency second input, the second magnitude input, and the second phase input, respectively.

25. Computer program product (1000) comprising instructions which, when the program is executed by a suitable processor, cause the processor to carry out any of the methods of claims 23-24.

Images