Method for operating a heat exchanger and system comprising a heat exchanger
Patent Information
- Application Number
- EP2023730723
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-05-27
- Filing Date
- 2023-05-25
- Publication Date
- 2025-04-09
AI Technical Summary
Heat exchangers face inefficiencies due to icing and contamination, which impede heat transfer and can lead to system failure, requiring inefficient or inadequate defrosting methods that consume excessive energy or fail to maintain operational reliability.
A method utilizing AI-based classification to monitor and determine optimal defrosting and cleaning times for heat exchangers, employing sensors and imaging devices to assess icing and contamination levels, allowing for precise control of defrosting processes and reducing the need for manual intervention.
This approach ensures efficient and reliable operation of heat exchangers by preventing premature or delayed defrosting, maintaining performance, and minimizing energy consumption by optimizing defrosting cycles based on real-time data analysis.
Smart Images

Figure 1.1
Abstract
Description
[0001] 'Method for operating a heat exchanger and system with a heat exchanger'
[0002] The present invention relates to a method for operating a heat exchanger and a system comprising a heat exchanger.
[0003] Heat exchangers are used to remove heat from a system to be cooled or to introduce heat into a system to be heated. In refrigeration, heat exchangers are used to remove heat from a volume to be cooled by converting a cooling medium from the liquid to the gaseous phase, with the heat exchanger acting as an evaporator. Similarly, in heating technology, a heat exchanger can be used to absorb ambient heat from the outside air and, in conjunction with a heat pump, provide heat for a building to be heated. Conversely, such a heat exchanger can also be used as a condenser or dry cooler to release heat to the environment.
[0004] Regardless of the specific application, it is crucial for the reliable and fault-free operation of the heat exchanger that heat transfer between the heat exchanger and its environment is not impaired by interference that isolates the heat exchanger from the environment. Such interference includes, for example, contamination or icing on the heat exchanger, which can accumulate between the fins or fin packs of the heat exchanger.
[0005] Heat exchangers often have fins or fin packs to provide the largest possible surface area for heat transfer while keeping the overall size small. During practical operation of such a heat exchanger, moisture from the area surrounding the fins can condense on their surfaces, causing these surfaces and the gaps between the fins to ice over. Due to the insulating effect of this icing, heat transfer between the area surrounding the heat exchanger and its fins or the corresponding liquid within the heat exchanger is impaired. In addition, air flow through the heat exchanger is impaired, increasing pressure loss and reducing performance because less air flows through the heat exchanger. In this state, the heat exchanger may no longer deliver the required cooling or heating capacity.This can lead to the destruction of the cooled goods or the failure of a system being cooled. Furthermore, icing can cause damage to the heat exchanger components.
[0006] To remove ice, it is common practice to defrost the heat exchanger using a heating device. This defrosting should be carried out as efficiently as possible. If defrosting occurs too frequently or for too long a period of time, an unnecessary amount of heat energy is introduced, for example, into the volume to be cooled, which then has to be removed using the heat exchanger to maintain or set the desired cooling temperature. If defrosting occurs too infrequently or for too short a period of time, the defrosting is ineffective and the functionality of the system in question is impaired. Common defrosting methods include electric defrosting, hot gas defrosting, warm brine defrosting, and water or air defrosting.
[0007] For example, document CN107091548A describes defrosting that is carried out using a camera and an AI-based image analysis.
[0008] Against this background, the present invention is based on the technical problem of specifying a method for operating a heat exchanger and a system with a heat exchanger, which in particular enable efficient defrosting and process-reliable operation of the heat exchanger.
[0009] According to a first aspect, the invention relates to a method comprising the method steps: operating a heat exchanger; monitoring the heat exchanger by means of at least one monitoring device, such as a sensor, an imaging device or the like; detecting a degree of icing and / or contamination of the heat exchanger and determining a defrosting time and / or cleaning time of the heat exchanger by evaluating data from the at least one monitoring device; wherein the evaluation of the data is carried out in a K1-based manner, wherein a K1-based classifier has two or more classes that define a degree of icing and / or contamination, and wherein the K1-based classifier assigns the data from the at least one monitoring device to one of the classes.Using the Cl-based classifier, a defrosting time and / or a cleaning time can be precisely determined, so that premature or delayed cleaning and / or defrosting can be avoided.
[0010] When the abbreviation “Kl” is used here, it stands for “artificial intelligence” and is a synonym for the related topics “machine learning” and “deep learning”.
[0011] The imaging device may be a camera. The imaging device may be an infrared camera. The imaging device may be a thermal imaging camera. The imaging device may be configured to generate photographic images in the visible wavelength range. The imaging device may be configured to generate photographic images in the non-visible wavelength range. The imaging device may be configured to generate thermal images.
[0012] When we refer to a visible wavelength range, we are referring to wavelengths that are visible to humans. When we refer to a non-visible wavelength range, we are referring to wavelengths that are invisible to humans.
[0013] It can be provided that, in addition to the Kl-based determination of a cleaning time and / or a defrosting time, a control of a defrosting process and / or a control of a cleaning process also takes place Kl-based.
[0014] According to one embodiment of the method, the classes, according to their ascending numbering, define an increasing degree of icing and / or contamination and / or an increasing defrosting and / or cleaning requirement. A class is defined as a threshold for the heat exchanger, and when this threshold is reached or exceeded, a defrosting and / or cleaning time is determined. For example, up to 10 classes, up to 20 classes, or up to 40 classes can be defined.
[0015] Depending on the design of the procedure, it may be provided that fewer than 10 classes are provided, for example three, four or five classes are provided.
[0016] According to one design of the procedure, exactly five classes are provided.
[0017] It can be provided that the number of classes is odd. Alternatively or additionally, it can be provided that the classes are assigned to groups, with a first group containing classes for whose degree of icing and / or soiling there is a need for defrosting and / or cleaning, and where the second group contains classes for whose degree of icing and / or soiling there is no need for defrosting and / or cleaning. Each group contains at least one class. The number of classes per group can be the same or different. If, for example, 10 classes are provided, it can be provided that 5 of the 10 classes are assigned to the first group and 5 of the 10 classes are assigned to the second group. If, for example, 11 classes are provided, it can be provided that 7 of the 11 classes are assigned to the first group and 4 of the 11 classes are assigned to the second group.For example, if four classes are planned, it can be specified that one of the four classes is assigned to the first group and three of the four classes are assigned to the second group. If, for example, six classes are planned, it can be specified that three of the six classes are assigned to the first group and three of the six classes are assigned to the second group.
[0018] According to one embodiment of the method, exactly five classes are provided, with three classes assigned to the first group and two classes assigned to the second group. A small number of classes simplifies the manual classification of training data.
[0019] In particular, it may be provided that the first group has more classes than the second group.
[0020] It may be provided that each of the groups has fewer than five classes.
[0021] Overall, the detection of a degree of icing and / or contamination of the heat exchanger and the resulting determination of whether defrosting and / or cleaning is required or not can be mapped as a classification problem using a classification algorithm. Training data is used to generate a mapping function which, based on sensor data or image data, classifies a degree of icing and / or contamination of the heat exchanger as either critical or non-critical, so that cleaning and / or defrosting is initiated or the heat exchanger can initially continue to operate without cleaning and / or defrosting. It can be provided that the mapping function is further improved based on the image data and sensor data processed during operation, resulting in a "learning" algorithm. In other words, the quality of the mapping function can be improved as the data set increases.
[0022] When sensor data is referred to here, it refers to one or more of the following values: temperature data of the environment and / or a refrigerant, pressure of a refrigerant, in particular at an inlet and outlet of the heat exchanger; air pressure, in particular a differential pressure between an ambient pressure and a pressure between a fan and a fin arrangement, whereby, for example, a pressure loss is measured on a side of a fin arrangement facing away from the fan.
[0023] According to one embodiment of the method, it can be provided that the Cl-based classifier is configured to determine a defrosting time and / or cleaning time for different heat exchangers, wherein the heat exchangers differ from one another with regard to their construction type and / or their operating conditions.
[0024] The types can differ, for example, in terms of the dimensions of the heat exchanger, the number of fans assigned to the heat exchanger, the number of heat exchangers, the power range, the design of the heat exchanger and the like.
[0025] The operating conditions can differ, for example, with regard to the ambient temperatures, ambient pressures, and ambient humidities expected during operation—in other words, with regard to their environmental conditions. The operating conditions can differ, for example, with regard to the area of application, for example, whether the heat exchanger is used in a cold storage room for food or in the open air. The operating conditions can also differ with regard to the number of additional heat exchangers arranged adjacent to the heat exchanger in question.
[0026] Depending on the design type and operating conditions, defrosting and / or cleaning of a heat exchanger in question may therefore be necessary sooner or later. For example, it may be possible to permit a higher degree of contamination and / or icing for a first heat exchanger, depending on its design type and operating conditions, than is possible for a second heat exchanger, depending on its design type and operating conditions. According to one embodiment of the method, it can be provided that for each of the different heat exchangers, depending on its design type, a class is defined as a respective threshold, and when this class is reached or exceeded, a defrosting time and / or cleaning time is defined, wherein the respective threshold is different for at least two of the different heat exchangers.In this way, heat exchangers of different types can be reliably operated under different operating conditions using a single Cl-based classifier.
[0027] Alternatively or additionally, it can be provided that for each of the different heat exchangers, classes are assigned to the first group and the second group depending on its design type, whereby the assignment of classes to the first group and the second group is different for at least two of the different heat exchangers. In this way, heat exchangers of different design types can be reliably operated under different operating conditions using a single Class-based classifier.
[0028] According to a further embodiment, the method can be characterized by operating a further heat exchanger; monitoring the further heat exchanger by means of at least one further monitoring device, such as a sensor, an imaging device, or the like; detecting a degree of icing and / or contamination of the further heat exchanger and determining a defrosting time and / or cleaning time of the further heat exchanger by evaluating data from the at least one further monitoring device;wherein the data is evaluated on a class-based basis using the class-based classifier, wherein the class-based classifier assigns the data of the at least one further monitoring device to one of the classes, and wherein the defrosting time and / or cleaning time of the heat exchanger for at least one degree of icing and / or contamination is defined differently from the defrosting time and / or cleaning time of the further heat exchanger for a substantially identical degree of icing and / or contamination. In this way, heat exchangers of different types can be reliably operated under different operating conditions using a single class-based classifier.
[0029] According to one embodiment of the method, it can be provided that the same database and the same Cl-based evaluation are used for both the heat exchanger and the additional heat exchanger. Alternatively or additionally, it can be provided that a plurality of heat exchangers are provided, wherein a defrosting time and / or cleaning time is determined on a Cl-based basis using the Cl-based classifier for each of the plurality of heat exchangers depending on its respective design type and / or its respective operating conditions.
[0030] Because the same database can be used across devices for two or more heat exchangers, a comprehensive database can be quickly built up to improve the quality of a mapping function of the Cl-based evaluation.
[0031] According to one embodiment of the method, manually classified reference data can be used as training data for the AI-based classifier. For this purpose, specialist personnel can, for example, manually classify image data and / or sensor data or data packets consisting of both image data and sensor data. Thus, several people can classify image data and / or sensor data or data packets into classes in order to classify the degree of icing and / or contamination of the heat exchanger in question. Based on this training data, an initial mapping function of the classifier can be generated, the quality of which can be subsequently improved by additional manually classified image data and / or sensor data or data packets and image data and / or sensor data or data packets classified during automated operation of the classifier.
[0032] According to one embodiment of the method, it can be provided that a control device of the heat exchanger is connected to a server, wherein the Cl-based classifier and / or a database of the Cl-based classifier are stored on the server.
[0033] Alternatively or additionally, it may be provided that parts of the database and / or the classifier are stored in a memory device of the control device. It may be provided that the control device has a computer for operating the classifier.
[0034] Alternatively or additionally, the database and / or the classifier can be stored entirely in the memory of the control device, and the classifier can be operated by the control device's computer. The control device can be provided with a wireless or wired data interface for data exchange with a server.
[0035] According to one embodiment of the method, it can be provided that two or more heat exchangers are provided, wherein a defrosting time and / or cleaning time is determined on a Kl-based basis by means of the Kl-based classifier for each of the two or more heat exchangers depending on its respective design type and / or its respective operating conditions, and wherein a defrosting sequence and / or cleaning sequence is determined based on the design type and / or the operating conditions and / or based on a degree of icing and / or a degree of contamination of a respective heat exchanger of the two or more heat exchangers.
[0036] According to one embodiment of the method, it can be provided that the two or more heat exchangers are arranged in a walk-in cold storage room, and defrosting of the heat exchangers takes place essentially one after the other, in particular essentially not simultaneously. If two or more heat exchangers are arranged together within a walk-in cold storage room, defrosting should, if possible, not take place simultaneously in order to keep the heat input into the cold storage room as low as possible and to keep the intended temperature of the cold storage room as constant as possible even during defrosting.
[0037] Alternatively or additionally, it can be provided that a defrosting sequence and / or cleaning sequence of the heat exchangers is carried out by a class-based setting of a respective class as a threshold for each of the heat exchangers, with the reaching or exceeding of which a defrosting time and / or a cleaning time is set.
[0038] If, for example, identical heat exchangers are arranged together in a walk-in cold room and, for each of the heat exchangers, class VI is defined as the threshold upon reaching which defrosting is initiated, the threshold for one of the heat exchangers can be reduced from class VI to class IV using the class in order to defrost this heat exchanger first.
[0039] The threshold reduction can then be repeated for each heat exchanger. After defrosting, the threshold for each heat exchanger can be reset to its original value.
[0040] Alternatively, the thresholds of the heat exchangers can be set differently for each heat exchanger, starting from Class VI, so that one heat exchanger is defrosted for an icing level of Class III, one heat exchanger for an icing level of Class IV, one heat exchanger for an icing level of Class V, and one heat exchanger for an icing level of Class VI. Here, too, the thresholds can be reset after each defrost. In this case, each defrost cycle can begin with a different heat exchanger, so that the threshold is lowered to Class III alternately for all heat exchangers, so that a different heat exchanger is defrosted first for each cycle.
[0041] Alternatively or additionally, it can be provided that a defrosting sequence and / or cleaning sequence of the heat exchangers is carried out by a class-based assignment of a respective class to the first or second group for each of the heat exchangers. From a technical point of view, the assignment of classes to the groups has essentially the same effect that has already been described for the setting of thresholds. Thus, based on the assignment of the classes to groups, it can be determined for which degree of icing and / or contamination defrosting or cleaning is necessary. If two or more heat exchangers are arranged together in a cooling volume, each of which is based on an identical assignment of the classes to the first group "defrosting" and to the second group "non-defrosting", the defrosting sequence can be determined by changing the assignment of the classes to the groups for one or more heat exchangers using the class.After defrosting, the assignment of classes to groups can be reset to the original state.
[0042] According to a second aspect, the invention relates to a system with a device, wherein the device has a heat exchanger with a heating device and / or with a cleaning device, wherein the device has a control device and at least one monitoring device, such as a sensor, an imaging device or the like, for monitoring the heat exchanger, with a K1-based classifier, wherein the control device is configured to carry out the following method steps: operating the heat exchanger; monitoring the heat exchanger by means of the at least one monitoring device; detecting a degree of icing and / or degree of contamination of the heat exchanger and determining a defrosting time and / or cleaning time of the heat exchanger by evaluating data from the at least one monitoring device;wherein the evaluation of the data is carried out on a Cl-based basis, wherein a Cl-based classifier has two or more classes that define a degree of icing and / or contamination, and wherein the Cl-based classifier assigns the data of the at least one monitoring device to one of the classes;
[0043] All aspects described above with regard to the method according to the invention can equally apply to the device according to the invention. Conversely, all aspects relating to the system according to the invention can be used in the method according to the invention.
[0044] According to one embodiment of the system, it can be provided that the Cl-based classifier is configured to determine a defrosting time and / or cleaning time for different heat exchangers, wherein the heat exchangers differ from one another with regard to their construction type and / or their operating conditions.
[0045] According to one embodiment of the system, it can be provided that the system has a further device, wherein the further device has a further heat exchanger with a further heating device and / or with a further cleaning device, wherein the further device has a further control device and at least one further monitoring device, such as a sensor, an imaging device or the like, for monitoring the further heat exchanger, wherein the further control device is set up to carry out the following method steps: operating the further heat exchanger; monitoring the further heat exchanger by means of the at least one further monitoring device;Detecting a degree of icing and / or contamination of the further heat exchanger and determining a defrosting time and / or cleaning time of the further heat exchanger by evaluating data from the at least one further monitoring device; wherein the evaluation of the data is carried out in a classifier-based manner, wherein the classifier-based classifier assigns the data from the at least one further monitoring device to one of the classes, wherein both the control device of the heat exchanger of the device and the further control device of the further heat exchanger of the further device are connected to a server, wherein the classifier-based classifier and / or a database of the classifier-based classifier is stored on the server.
[0046] According to one embodiment of the system, it can be provided that the same database and the same AI-based evaluation are used for both the heat exchanger of the device and the heat exchanger of the additional device. According to one embodiment of the system, it can be provided that the defrosting time and / or cleaning time of the heat exchanger is defined for at least one degree of icing and / or contamination differently from the defrosting time and / or cleaning time of the additional heat exchanger with essentially the same degree of icing and / or contamination.
[0047] According to one embodiment of the system, manually classified reference data may serve as the basis for the Cl-based classifier.
[0048] According to one embodiment of the system, it can be provided that a plurality of devices with heat transfer are provided, wherein a defrosting time and / or cleaning time is determined on a Kl-based basis by means of the Kl-based classifier for each of the plurality of devices.
[0049] According to one embodiment of the system, it can be provided that the system is designed to carry out a method according to the invention for one heat exchanger or for several heat exchangers.
[0050] The invention is described in more detail below with reference to drawings illustrating exemplary embodiments. Each drawing shows a schematic diagram.
[0051] Fig. 1 shows a system according to the invention in a perspective view;
[0052] Fig. 2 the system from Fig. 1 without housing in a perspective view;
[0053] Fig. 3 shows the heat exchanger of the system from Fig. 1 with continuous heating elements;
[0054] Fig. 4 shows a heat exchanger for a system according to Fig. 1 with non-continuous heating elements;
[0055] Fig. 5 Icing conditions of the heat exchanger from Fig. 3;
[0056] Fig. 6 is a flowchart of a method according to the invention;
[0057] Fig. 7 shows a system according to the invention with several devices and a server;
[0058] Fig. 8 shows the system of Fig. 7 in a cold storage room; Fig. 9 shows another system according to the invention with several devices and a server.
[0059] Fig. 1 shows a system 1 according to the invention with a device 2. The device 2 is a cooling system 2. The cooling system 2 can be used, for example, to cool a walk-in cooling volume.
[0060] The cooling system 2 has a housing 4 that supports protective grilles 6 of fans 8 of the cooling system 2. The fans 8 serve to convey air of an environment U along fins 10 of a heat exchanger 12 of the cooling system 2. The heat exchanger 12 is described below with reference to Fig. 2.
[0061] The heat exchanger 12 is located inside the cooling system 2, so that the housing 4 is hidden in Fig. 2 to illustrate the heat exchanger 12.
[0062] The heat exchanger 12 has a plurality of flat or plate-shaped fins 10 which are arranged essentially parallel to one another along a longitudinal extent L of the heat exchanger 12.
[0063] The fins 10 are penetrated by a pipe 14 of the heat exchanger 12, which carries a cooling medium. The fins 10 can also be referred to as cooling fins 10. The cooling fins 10 are connected to the pipe 14 of the heat exchanger 12.
[0064] The device 2 has a heating device 16 with heating rods 18 for defrosting the heat exchanger 12. The heating rods 18 also penetrate the cooling fins 10 along the longitudinal direction L and are connected to the cooling fins 10.
[0065] The device 2 has a cleaning device 13 with cleaning nozzles 15, which spray a cleaning fluid, such as water or the like, onto the lamellae 10 to remove dirt.
[0066] Fig. 3 shows the cooling fins 10 of the heat exchanger 12 with the heating rods 18 and the pipe 14. According to Fig. 3, the heating rods 18 penetrate the arrangement of the fins 10 completely over the entire length when viewed along the longitudinal direction L.
[0067] Fig. 4 shows an alternative embodiment of a heat exchanger 12', which can equally be used in a device 2 according to the invention. The heat exchanger 12' according to Fig. 4 differs from the heat exchanger 12 according to Fig. 3 in that heating rods 18' are provided which penetrate the arrangement of fins 10 only over a partial length, viewed along the longitudinal direction L.
[0068] As shown in Fig. 2, the device 2 comprises a device 20 for photographic imaging and a control device 22.
[0069] The device 20 for photographic imaging is a camera 20 which is configured both for photographic imaging in the visible wavelength range and for photographic imaging in the non-visible wavelength range and for this purpose has a sensor 24 for corresponding imaging in the said wavelength range.
[0070] The device 20 for photographic imaging serves to generate photographic images of the heat exchanger 12 and transmit them to a control device 22 of the device 2. The control device 22 can have a computer for evaluating photographic images, be connected to a computer for evaluating photographic images, and / or be connected to a server for evaluating photographic images.
[0071] The device 2 also has a temperature sensor 26, a pressure sensor 28 and a humidity sensor 30, which transmit signals to the control device 22.
[0072] The photographic imaging device 20, the temperature sensor 26, the pressure sensor 28 and the humidity sensor 30 are monitoring devices for monitoring the heat exchanger 12.
[0073] The control device is configured to carry out the method steps described below with reference to Fig. 6.
[0074] The flow chart 32 according to Fig. 6 relates to the operation of the heat exchanger 12 of the device 2.
[0075] Block 34 of flowchart 32 describes the sensor level of the method and represents signals from sensors 26, 28, and 30 as well as the provision of photographic images of heat exchanger 12. Block 34 thus represents the input data of the method according to the invention, which is transmitted to a database 36. These data are subsequently processed or prepared in a further method step, which is represented by block 38.
[0076] According to step 40, a check is made to determine whether the heating device 16 and / or the cleaning device 13 is switched on or whether a defrosting process and / or cleaning process is currently active. If the heating device 16 and / or the cleaning device 13 is not switched on and thus no defrosting process and / or cleaning process is active, method branch 42 is executed, which relates to detecting the icing state and / or contamination state of the heat exchanger 12 and determining a defrosting time and / or cleaning time of the heat exchanger 12. If the heating device 16 and / or the cleaning device 13 is switched on and thus the defrosting process and / or cleaning process is active, method branch 44 is executed, which relates to controlling the defrosting process and / or the cleaning process.
[0077] First, the process steps of process branch 42 are described.
[0078] In a method step 46, a photographic image of the heat exchanger 12 and / or sensor data from the sensors 26, 28, 30 are evaluated. The evaluation is carried out using a software that is Kl-based, namely a Kl-based classification
[0079] The photographic image was created by means of the photographic imaging device 20.
[0080] The Kl model underlying method steps 46 was generated using training data represented by block 48. In particular, block 48 represents a machine learning, i.e., a statistical model based on reference data manually evaluated and classified by specialist personnel. The Kl model is therefore based on reference data and reference images in the form of photographs, with the reference images being shown as examples in Fig. 5.
[0081] Here, a first group 50 shows reference images 52 for an icing and / or contamination state of the heat exchanger 12 that requires defrosting and / or cleaning. Furthermore, a second group 54 shows reference images 52 for an icing and / or contamination state of the heat exchanger 12 that does not require defrosting and / or cleaning. The reference images 52 of the heat exchanger 12 have been divided into ten classes according to the degree of icing and / or contamination evident in the reference images 52. These classes are numbered sequentially from I to X, with the degree of icing and / or contamination increasing with increasing numbering.
[0082] The reference images 52 with the icing degree and / or contamination degree I, II, III, IV and V have been assigned to the second group 54, while the reference images with the icing degree and / or contamination degree VI, VII, VIII, IX, X have been assigned to the first group 50.
[0083] A picture 56 of the heat exchanger 12 according to Fig. 6, created by means of the device 20 for photographic imaging, is assigned to a class I -X in a method step 58 by means of the class model 46 and, based on the assigned class, in a method step 60, it is determined on the basis of the associated group 50, 54 whether defrosting and / or cleaning of the heat exchanger 12 is necessary or not.
[0084] If no defrosting and / or cleaning is required, branch 42 restarts as a loop according to path 64 starting from branch 62.
[0085] If defrosting and / or cleaning is required, a defrosting time and / or cleaning time is set according to block or process step 66 to initiate the defrosting and / or cleaning. With the start of the defrosting process and / or cleaning process, process branch 44 of flowchart 32 is therefore executed, since the query or condition 40 now leads to process branch 44 due to the switched-on heating device 16 and / or cleaning device 13.
[0086] The defrosting of the heat exchanger 12 is controlled by evaluating further photographic images 68 and / or sensor data from the sensors 26, 28, 30.
[0087] The evaluation of the further photographic images 68 is also based on a class model 70, which was generated on the basis of training data in a machine learning process according to method step 72. In particular, block 72 represents a machine learning, i.e., a statistical model, based on reference images manually evaluated and classified by specialist personnel.
[0088] With the method steps 74 and 76, analogous to the procedure described above with regard to the photographic images 56, the further photographic images 68 can be assigned to a class in order to stop the defrosting process depending on an icing condition of the heat exchanger 12.
[0089] If a cleaning process is triggered, it can be controlled on a time-based basis, for example, whereby the cleaning device is switched on for a specified period of time.
[0090] If the assignment of the further photographic image 68 to a class indicates that further defrosting is required, branch 44 is repeated according to path 80. If the assignment of the further photographic image 68 to a class indicates that no further defrosting is required, path 82 leads to process step 84, which causes the heating device 16 to be switched off.
[0091] Due to the switched off heating device 16, the branch 42 is now run through again in a loop until a necessary defrosting and / or cleaning of the heat exchanger 12 is detected.
[0092] The signals of the sensors 26, 28, 30 can be used to check the plausibility of the image evaluation both during the detection of the icing condition and / or contamination condition and during the control of the defrosting process and / or the cleaning process.
[0093] According to an alternative embodiment, the device 20 for photographic imaging may be arranged within the housing 4. In particular, the device 20 for photographic imaging may be arranged within the housing 4 between the fans 8 and the heat exchanger 12.
[0094] It can be provided that the heat exchanger according to an alternative embodiment is a so-called microchannel heat exchanger, which has, for example, parallel pipes for carrying a cooling medium and fins arranged therebetween.
[0095] The Cl-based classifier 40 can be configured to determine a defrosting time and / or cleaning time for different heat exchangers, wherein the heat exchangers differ from one another in terms of their construction type and / or operating conditions. Fig. 7 shows another system T according to the invention, which comprises a plurality of devices 2, 2', 2", 2'". The devices 2', 2", 2'" comprise the same monitoring devices that have already been described with reference to device 2.
[0096] Each of the devices 2, 2', 2", 2'" is connected with its associated control unit to a server 86 which has reference data and / or the classifier 46, 70 for carrying out the method according to the invention.
[0097] The devices 2, 2', 2", 2'" differ from one another with regard to their construction type and / or their ambient conditions. It is provided that the defrosting time and / or cleaning time of a respective heat exchanger of one of the respective devices 2, 2', 2", 2'" is defined for at least one degree of icing and / or contamination differently from the defrosting time and / or cleaning time of a heat exchanger of another of the respective devices 2, 2', 2", 2'" with essentially the same degree of icing and / or contamination.
[0098] This can be achieved, for example, in that the classes, according to their numbering, define an increasing degree of icing and / or contamination and / or an increasing defrosting and / or cleaning requirement, wherein a class is defined as a threshold for the heat exchanger of a respective device 2, 2', 2", 2'", and when this threshold is reached or exceeded, a defrosting time and / or a cleaning time is set, and in that for each respective heat exchanger of the various devices 2, 2', 2", 2'", and when this threshold is reached or exceeded, a class is defined as a respective threshold, and when this threshold is reached or exceeded, a defrosting time and / or a cleaning time is set, wherein the respective threshold is different for at least two of the respective different devices 2, 2', 2", 2'".
[0099] Alternatively, this can be achieved by assigning the classes to groups, wherein a first group contains classes for whose degree of icing and / or degree of soiling there is a need for defrosting and / or cleaning and wherein the second group contains classes for whose degree of icing and / or degree of soiling there is no need for defrosting and / or cleaning and that for each of the respective different devices 2, 2', 2", 2'", depending on their type of construction and / or their ambient conditions, the classes are assigned to the first group and to the second group, wherein the assignment of the classes to the first group and to the second group is different for at least two of the respective different devices 2, 2', 2", 2'".
[0100] Thus, the same database and the same Cl-based evaluation can be used for the heat exchangers of all devices 2, 2', 2", 2'".
[0101] The devices 2, 2', 2", 2'" can be arranged spatially separate from one another or together in a room. In the event that the devices 2, 2', 2", 2'" are arranged in a room, the software (Kl) can, as required, shift a threshold for one or more devices 2, 2', 2", 2'" for defrosting and / or adjust the assignment of the classes to the first or second group for one or more of the devices 2, 2', 2", 2'" and / or prioritize defrosting based on the degree of icing.
[0102] In this way, a defrosting sequence can be defined, whereby in particular no simultaneous defrosting of devices 2, 2', 2", 2'" or their heat exchangers arranged together in a room takes place.
[0103] Fig. 8 shows the system 1' from Fig. 7 in a cold room K. Only three devices 2, 2', 2" are shown.
[0104] For the system according to Fig. 7, it is provided that a defrosting time of a respective heat exchanger of a respective device 2, 2', 2" is determined on a Cl-based basis by means of the Cl-based classifier, wherein a defrosting sequence is determined by means of the Cl, so that defrosting of the heat exchangers of the devices 2, 2', 2" does not take place simultaneously.
[0105] For this purpose, it is provided that the defrosting sequence of the heat exchangers of the devices 2, 2', 2" is carried out by a class-based setting of a respective class (I - X) as a threshold for each of the heat exchangers of the devices 2, 2', 2", upon reaching or exceeding which a defrosting time is set.
[0106] In this case, identical heat exchangers of devices 2, 2', 2" are arranged together in the walk-in cold room K. For each of the heat exchangers of devices 2, 2', 2", class VI is defined as the threshold upon reaching which defrosting is initiated. For one of the heat exchangers of devices 2, 2', 2" the threshold is reduced from class VI to class IV using the Kl in order to defrost this heat exchanger first. The reduction of the threshold is then repeated for each of the heat exchangers of devices 2, 2', 2". After defrosting, the threshold of the respective heat exchanger of devices 2, 2', 2" can be reset to the original value (class VI).
[0107] Fig. 9 shows a further system 1" according to the invention with a plurality of devices 2, 2"", 2""', 2""' and a server 86. The method according to the invention can be used for devices with heat exchangers of different construction types, wherein for each of the devices 2, 2"", 2""', 2""' a threshold for defrosting and / or cleaning can be defined individually or an assignment of the classes to the first or second group can be defined. The devices 2, 2, 2""', 2""' can be set up for use indoors or outdoors. The devices 2, 2"", 2""', 2""' can be condensers, evaporators, recoolers or the like of cooling systems and / or heating systems or can be used in heating technology and / or cooling technology.
[0108] List of reference symbols
[0109] 2 Device I Cooling system
[0110] 2' Device I Cooling system
[0111] 2" device I cooling system
[0112] 2'“ device I cooling system
[0113] 4 housings
[0114] 6 protective grilles
[0115] 8 fans
[0116] 10 fins / cooling fins 10
[0117] 12 heat exchangers
[0118] 12 heat exchangers
[0119] 13 Cleaning device
[0120] 14 Pipeline
[0121] 15 cleaning nozzles
[0122] 16 Heating device
[0123] 18 heating elements
[0124] U environment
[0125] L longitudinal direction
[0126] 20 Photographic imaging facility
[0127] 22 Control device
[0128] 22' control device
[0129] 22" control device
[0130] 22" control unit
[0131] 24 sensors
[0132] 26 Temperature sensor
[0133] 28 Pressure sensor
[0134] 30 Humidity sensor
[0135] 32 Flowchart
[0136] 34 Block / Input data / Input signals
[0137] 36 Database
[0138] 38 Block / Processing
[0139] 40 Condition / Branch
[0140] 42 Branch “Detecting the icing condition”
[0141] 44 Branch “Defrost Control”
[0142] 46 Class Model / Evaluation / Classifier
[0143] 48 Training Data / Machine Learning
[0144] 50 first group of reference images 52 reference image
[0145] 54 second group of reference images
[0146] 56 Recording of the visible wavelength range
[0147] 58 Process step
[0148] 60 process steps
[0149] 62 Condition / Branch
[0150] 64 Path
[0151] 66 process steps
[0152] 68 Recording of the non-visible wavelength range
[0153] 70 Class Model / Evaluation / Classifier
[0154] 72 Training Data / Machine Learning
[0155] 74 Process step
[0156] 76 process steps
[0157] 78 Condition / Branch
[0158] 80 Path
[0159] 82 Path
[0160] 84 Process step
[0161] 86 servers
Claims
Claims 1. Procedure, with the following procedural steps: Operating a heat exchanger (12, 12'); Monitoring the heat exchanger (12, 12') by means of at least one Monitoring device, such as a sensor (26, 28, 30), an imaging device (20) or the like; Detecting a degree of icing and / or soiling of the heat exchanger (12, 12') and determining a defrosting time and / or cleaning time of the heat exchanger (12, 12') by evaluating data from at least one monitoring device; - where the evaluation of the data is AI-based, - wherein a KL-based classifier (46, 70) has two or more classes (I - X) that define a degree of icing and / or pollution and - wherein the class-based classifier (46, 70) assigns the data of the at least one monitoring device to one of the classes, characterized in that the classes (I - X) define an increasing degree of icing and / or soiling and / or an increasing defrosting and / or cleaning requirement in ascending order of their numbering, wherein a class is defined as a threshold for the heat exchanger, upon reaching or exceeding which a defrosting time and / or a cleaning time is defined, and / or the classes (I - X) are assigned to groups (50, 54), wherein a first group (50) contains classes (VI - X) for which a defrosting and / or cleaning requirement exists, and wherein the second group (54) contains classes (I - IV) contains items for which there is no need for defrosting and / or cleaning due to the degree of icing and / or soiling.
2. Method according to claim 1, characterized in that the KL-based classifier (46, 70) is configured to determine a defrosting time and / or cleaning time for different heat exchangers (12, 12'), wherein the heat exchangers (12, 12') differ from each other with respect to their design type and / or their operating conditions. CORRECTED SHEET (RULE 91) ISA / EP A method according to claim 2, characterized in that for each of the respective different heat exchangers (12, 12'), a class (I-X) is defined as a respective threshold depending on its design type and / or its ambient conditions, upon reaching or exceeding which a defrosting time and / or a cleaning time is defined, wherein the respective threshold is different for at least two of the respective different heat exchangers (12, 12') and / or for each of the respective different heat exchangers (12, 12'), an assignment of classes to the first group (50) and to the second group (54) is made depending on its design type, wherein the assignment of classes (I-X) to the first group (50) and to the second group (54) is different for at least two of the respective different heat exchangers (12, 12'). A method according to claim 2 or 3, characterized by Operating another heat exchanger (12, 12'); Monitoring the further heat exchanger (12, 12') by means of at least one further monitoring device, such as a sensor, an imaging device or the like; Detecting a degree of icing and / or soiling of the further heat exchanger (12, 12') and determining a defrosting time and / or cleaning time of the further heat exchanger (12, 12') by evaluating data from at least one further monitoring device; - where the evaluation of the data is AI-based using the AI-based classifier (46, 70), - wherein the KL-based classifier (70, 72) assigns the data of at least one further monitoring device to one of the classes (I - X) and - wherein the defrosting time and / or cleaning time of the heat exchanger (12, 12') is defined differently for at least one degree of icing and / or soiling than the defrosting time and / or cleaning time of the further heat exchanger (12, 12') at substantially the same degree of icing and / or soiling. Method according to claim 4, CORRECTED SHEET (RULE 91) ISA / EP characterized in that the same data basis and the same AI-based evaluation are used for both the heat exchanger (12, 12') and the further heat exchanger (12, 12') and / or a plurality of heat exchangers (12, 12') are provided, wherein a defrosting time and / or cleaning time is determined AI-based by means of the AI-based classifier for each of the plurality of heat exchangers (12, 12') depending on its respective design type and / or its respective operating conditions.A method according to any one of the preceding claims, characterized in that manually classified reference data serves as training data for the AI-based classifier (46, 70) and / or exactly five classes are provided, wherein three classes are assigned to the first group and two classes are assigned to the second group; and / or the first group has more classes than the second group and / or each of the groups has fewer than five classes. A method according to any one of the preceding claims, characterized in that a control unit (22, 22', 22", 22'", 22"", 22""', 22""") of the heat exchanger (12, 12') is connected to a server (86), wherein the AI-based classifier (40, 76) and / or a database (36) of the AI-based classifier (40, 76) are stored on the server (86).Method according to one of the preceding claims, characterized in that two or more heat exchangers (12, 12') are provided, wherein a defrosting time and / or cleaning time is determined using the classifier based on the classifier for each of the two or more heat exchangers (12, 12') depending on its respective design type and / or its respective operating conditions, and. CORRECTED SHEET (RULE 91) ISA / EP wherein a defrosting sequence and / or cleaning sequence is determined based on the design type and / or operating conditions and / or on a degree of icing and / or fouling of a respective heat exchanger of the two or more heat exchangers, in particular that the two or more heat exchangers are arranged in a walk-in cold room and defrosting of the heat exchangers is carried out substantially sequentially, in particular not substantially simultaneously, and / or a defrosting sequence and / or cleaning sequence of the heat exchangers is determined by a class-based determination of a respective class as a threshold for each of the heat exchangers,Upon reaching or exceeding these limits, a defrosting time and / or a cleaning time is determined, and / or a defrosting sequence and / or cleaning sequence of the heat exchangers is determined by assigning a respective class to the first or second group for each of the heat exchangers. System comprising a device (2, 2' , 2“, 2'“, 2““, 2““', 2““'), wherein the device (2, 2', 2“, 2'“, 2““', 2““') comprises a heat exchanger (12) with a heating device (16) and / or with a cleaning device (13), wherein the device (2, 2', 2“, 2'“, 2““, 2““', 2““') comprises a control device (22, 22', 22“, 22'“) and at least one monitoring device, such as a sensor (26, 28, 30), an imaging device (20) or the like, for monitoring the heat exchanger (12, 12'), with a KL-based classifier (46, 70), wherein the control device (22, 22', 22“, 22'“, 22““, 22“'“, 22““”) is set up for this purpose,to carry out the following procedural steps: - Operating the heat exchanger (12, 12'); - Monitoring of the heat exchanger (12, 12') by means of at least one monitoring device; - Detecting the degree of icing and / or fouling of the heat exchanger (12, 12') and determining the defrosting time and / or cleaning time of the heat exchanger (12, 12') by evaluating data from at least one monitoring device; wherein the evaluation of the data is based on Cl, CORRECTED SHEET (RULE 91) ISA / EP wherein a classifier-based classifier (46, 70) has two or more classes (I - X) that define a degree of icing and / or degree of soiling, and wherein the classifier-based classifier (46, 70) assigns the data of the at least one monitoring device to one of the classes (I - X). System according to claim 9, characterized in that the classifier-based classifier (46, 70) is configured to determine a defrosting time and / or cleaning time for different heat exchangers (12, 12'), wherein the heat exchangers (12, 12') differ from one another with respect to their design type and / or their operating conditions.System according to claim 10, characterized in that the system (1 , T, 1") comprises a further device (2, 2', 2", 2'", 2"", 2""', 2""') wherein the further device (2, 2', 2", 2'", 2"", 2""', 2""') comprises a further heat exchanger (12, 12') with a further heating device and / or with a further cleaning device, wherein the further device (2, 2', 2", 2'", 2"", 2""', 2""') comprises a further control device (22, 22', 22", 22'", 22"", 22""', 22""") and at least one further monitoring device, such as a sensor, an imaging device or the like, for monitoring the further heat exchanger (12, 12'), wherein the further control device (22, 22', 22“, 22'“, 22““, 22“'“, 22““”) is set up to carry out the following procedural steps:. - Operation of the further heat exchanger (12, 12'); - Monitoring of the further heat exchanger (12, 12') by means of at least one further monitoring device; - Detecting a degree of icing and / or fouling of the further heat exchanger (12, 12') and determining a defrosting time and / or cleaning time of the further heat exchanger (12, 12') by evaluating data from the at least one further monitoring device; wherein the evaluation of the data is class-based, wherein the class-based classifier (46, 70) assigns the data from the at least one further monitoring device to one of the classes, wherein both the control device (22, 22', 22", 22'", 22"", 22""', 22""") of the heat exchanger (12, 12') of the device (2, 2', 2", 2'", 2"", 2""', 2""') and the CORRECTED SHEET (RULE 91) ISA / EP A further control unit of the further heat exchanger (12, 12') of the further device (22, 22', 22", 22'") is connected to a server (86), wherein the AI-based classifier (46, 70) and / or a database (36) of the AI-based classifier is stored on the server (86). System according to claim 11, characterized in that the same database and the same AI-based evaluation are used both for the heat exchanger (12, 12') of the device (2, 2', 2", 2'", 2"", 2""', 2""') and for the heat exchanger (12, 12') of the further device (2, 2', 2", 2'", 2"", 2""', 2""').A system according to claim 11 or 12, characterized in that the defrosting time and / or cleaning time of the heat exchanger (12, 12') is defined differently for at least one degree of icing and / or fouling than the defrosting time and / or cleaning time of the further heat exchanger (12, 12') at substantially the same degree of icing and / or fouling. A system according to any one of claims 9 to 13, characterized in that manually classified reference data serve as the basis for the AI-based classifier (46, 70). System according to one of claims 9 - 14, characterized in that a plurality of devices (2, 2', 2", 2'", 2"", 2""', 2""') are provided, wherein a defrosting time and / or cleaning time is determined using the classifier (40, 76) for each of the plurality of devices (2, 2', 2", 2'", 2"", 2""', 2""').System according to one of claims 9 - 15, characterized in that the system (1 , T, T) is configured to carry out a method according to one of claims 1 - 8 for a heat exchanger (12, 12') or for several heat exchangers (12, 12'). CORRECTED SHEET (RULE 91) ISA / EP