Ultra-low temperature freezer and energy-saving operation control method therefor

Abstract

The present invention relates to the technical field of refrigeration. Provided are an ultra-low temperature freezer and an energy-saving operation control method therefor. The ultra-low temperature freezer comprises: a temperature sensor group, a first-stage compressor, a second-stage compressor, an intermediate heat exchanger and a controller, wherein the temperature sensor group comprises a first temperature sensor and a second temperature sensor; the first-stage compressor is used for cooling the intermediate heat exchanger; the second-stage compressor is used for cooling the space in a cabinet body of the ultra-low temperature freezer, and conducting heat to the intermediate heat exchanger; and the controller is used for: at a starting moment of a subsequent control cycle, setting the cooling power of the first-stage compressor to be an adjusted first cooling power, and setting the cooling power of the second-stage compressor to be an adjusted second cooling power. According to the present invention, the cooling power of a compressor can be automatically adjusted, so as to implement control over the temperature stability and power accuracy of a freezer, thereby reducing energy consumption.

Description

Ultra-low temperature freezer and energy-saving operation control method thereof Technical Field

[0001] The present invention relates to the field of refrigeration technology, and in particular to an ultra-low temperature freezer and an energy-saving operation control method thereof. Background Art

[0002] Among the current related technologies, although ultra-low temperature freezers can realize the function of ultra-low temperature storage and have good thermal insulation performance, due to inaccurate temperature control and power regulation, there are problems of energy waste and excessive energy consumption costs.

[0003] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art.

[0004] Summary of the Invention

[0005] The present invention provides an ultra-low temperature freezer and an energy-saving operation control method thereof, which can solve the technical problem of inaccurate temperature control and power regulation of the ultra-low temperature freezer.

[0006] According to a first aspect of the present invention, there is provided an ultra-low temperature freezer, comprising:

[0007] Temperature sensor group, primary compressor, secondary compressor, intermediate heat exchanger and controller;

[0008] The temperature sensor group includes a first temperature sensor and a second temperature sensor, wherein the first temperature sensor is used to detect first temperature data in the intermediate heat exchanger, and the second temperature sensor is used to detect second temperature data in the cabinet of the ultra-low temperature freezer;

[0009] The primary compressor is used to cool the intermediate heat exchanger;

[0010] The secondary compressor is used to cool the space inside the ultra-low temperature freezer and transfer the heat to the intermediate heat exchanger;

[0011] The controller is used to:

[0012] At multiple moments in the current control cycle, respectively acquiring first temperature data detected by the first temperature sensor and second temperature data detected by the second temperature sensor;

[0013] determining a first refrigeration power of the primary compressor and a second refrigeration power of the secondary compressor in a current control cycle;

[0014] Inputting the first temperature data, the second temperature data, the first refrigeration power, and the second refrigeration power into a temperature prediction model to obtain second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, and first predicted temperature data inside the intermediate heat exchanger;

[0015] determining, based on the first predicted temperature data and the second predicted temperature data, whether the first cooling power and the second cooling power meet a preset adjustment condition;

[0016] If the first cooling power and the second cooling power meet the preset adjustment conditions, then obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model;

[0017] At the start time of the next control cycle, the refrigeration power of the first-stage compressor is set to the adjusted first refrigeration power, and the refrigeration power of the second-stage compressor is set to the adjusted second refrigeration power.

[0018] According to a second aspect of the present invention, there is provided a method for controlling energy-saving operation of an ultra-low temperature freezer, comprising:

[0019] At multiple moments in the current control cycle, first temperature data detected by the first temperature sensor and second temperature data detected by the second temperature sensor are respectively acquired;

[0020] determining a first refrigeration power of the primary compressor and a second refrigeration power of the secondary compressor in a current control cycle;

[0021] Inputting the first temperature data, the second temperature data, the first refrigeration power, and the second refrigeration power into a temperature prediction model to obtain second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, and first predicted temperature data inside the intermediate heat exchanger;

[0022] determining, based on the first predicted temperature data and the second predicted temperature data, whether the first cooling power and the second cooling power meet a preset adjustment condition;

[0023] If the first cooling power and the second cooling power meet the preset adjustment conditions, then obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model;

[0024] At the start time of the next control cycle, the refrigeration power of the first-stage compressor is set to the adjusted first refrigeration power, and the refrigeration power of the second-stage compressor is set to the adjusted second refrigeration power.

[0025] Technical effect: According to the present invention, by detecting the temperature data of the intermediate heat exchanger and the inside of the freezer respectively through two temperature sensors, precise control of the temperature inside the freezer can be achieved. This precise control is very important for applications that require maintaining ultra-low temperatures, such as biomedical research and other fields. The refrigeration power of the first-stage compressor and the second-stage compressor is adjusted through the temperature prediction model and the power setting model, thereby achieving control of the temperature stability and power accuracy of the freezer and efficient use of energy. The controller determines whether the refrigeration power needs to be adjusted based on the preset adjustment conditions, thereby reducing the refrigeration power of the first-stage compressor and the second-stage compressor while meeting the temperature requirements, thereby minimizing energy consumption. When judging whether the refrigeration power of the next control cycle can be adjusted, the first condition and the second condition can be determined based on the actual demand for the temperature inside the intermediate heat exchanger and the ultra-low temperature freezer. When the first condition and the second condition are met at the same time, it can be determined that the current refrigeration power is high, and the refrigeration power can be appropriately reduced to save energy while making the temperature control more precise. When training the temperature prediction model, the difference between sample temperature data and predicted temperature data can be determined. Weights are set based on the principle that shorter time intervals from the start time yield higher accuracy, and that the closer the cooling power in the current control cycle is to the cooling power in the historical control cycle, the closer the temperature is, and the greater the reference value of the temperature error. A weighted summation of the j-th temperature error output by the temperature prediction model at each moment is then performed to obtain a loss function. This improves the accuracy and objectivity of the loss function, thereby increasing training efficiency and the accuracy of the temperature prediction model. When determining the constraints for the power setting model, the adjusted primary and secondary cooling powers can be kept within an appropriate range. This calculation, based on the current temperature data and the output of the prediction model, can reduce overcooling and energy consumption. The adjusted predicted temperature within the intermediate heat exchanger is within the set temperature range, allowing the refrigeration system to maintain temperature control requirements and reducing overheating or underheating. The adjusted predicted temperature within the ultra-low temperature freezer is less than or equal to the set ultra-low temperature freezer temperature multiplied by a preset coefficient, meeting refrigeration requirements and reducing the risk of refrigerated items deteriorating due to overheating. This improves the stability, efficiency, and temperature control capabilities of the refrigeration system, providing reliable cooling and refrigeration capabilities. When determining the objective function of the power setting model, the cooling power can be adjusted to the minimum. By minimizing power, energy efficiency optimization and energy conservation and emission reduction can be achieved. Minimizing cooling power reduces equipment energy consumption and provides more efficient refrigeration system operation while maintaining cooling performance.

[0026] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and not limiting of the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without inventive work.

[0028] FIG1 exemplarily shows a schematic diagram of an ultra-low temperature freezer according to an embodiment of the present invention;

[0029] FIG2 exemplarily shows a flow chart of an energy-saving operation control method of an ultra-low temperature freezer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0031] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0032] FIG1 exemplarily shows a schematic diagram of an ultra-low temperature freezer according to an embodiment of the present invention, wherein the freezer comprises:

[0033] Temperature sensor group, primary compressor, secondary compressor, intermediate heat exchanger and controller;

[0034] The temperature sensor group includes a first temperature sensor and a second temperature sensor, wherein the first temperature sensor is used to detect first temperature data in the intermediate heat exchanger, and the second temperature sensor is used to detect second temperature data in the cabinet of the ultra-low temperature freezer;

[0035] The primary compressor is used to cool the intermediate heat exchanger;

[0036] The secondary compressor is used to cool the space inside the ultra-low temperature freezer and transfer the heat to the intermediate heat exchanger;

[0037] The controller is used to:

[0038] At multiple moments in the current control cycle, respectively acquiring first temperature data detected by the first temperature sensor and second temperature data detected by the second temperature sensor;

[0039] determining a first refrigeration power of the primary compressor and a second refrigeration power of the secondary compressor in a current control cycle;

[0040] Inputting the first temperature data, the second temperature data, the first refrigeration power, and the second refrigeration power into a temperature prediction model to obtain second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, and first predicted temperature data inside the intermediate heat exchanger;

[0041] determining, based on the first predicted temperature data and the second predicted temperature data, whether the first cooling power and the second cooling power meet a preset adjustment condition;

[0042] If the first cooling power and the second cooling power meet the preset adjustment conditions, then obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model;

[0043] At the start time of the next control cycle, the refrigeration power of the first-stage compressor is set to the adjusted first refrigeration power, and the refrigeration power of the second-stage compressor is set to the adjusted second refrigeration power.

[0044] According to the ultra-low temperature freezer of an embodiment of the present invention, two temperature sensors are used to detect the temperature data of the intermediate heat exchanger and the inside of the freezer respectively, so as to achieve precise control of the temperature inside the freezer. This precise control is very important for applications that need to maintain ultra-low temperatures, such as biomedical research and other fields. The refrigeration power of the first-stage compressor and the second-stage compressor is adjusted through the temperature prediction model and the power setting model, thereby achieving control of the temperature stability and power accuracy of the freezer and efficient use of energy. The controller determines whether the refrigeration power needs to be adjusted based on the preset adjustment conditions, thereby reducing the refrigeration power of the first-stage compressor and the second-stage compressor while meeting the temperature requirements, thereby minimizing energy consumption.

[0045] According to one embodiment of the present invention, each control cycle can be set to 10 minutes, 15 minutes, etc., and a time period can be set to half a minute, one minute, etc., although this is not a limitation of the present invention. By acquiring the first and second temperature data, the controller can determine the temperature changes of the intermediate heat exchanger and the interior space of the refrigerator. This data will serve as input for subsequent control steps to determine the cooling power of the primary and secondary compressors and to perform temperature prediction and adjustment.

[0046] According to one embodiment of the present invention, cooling power refers to the power consumption of a compressor per unit time. There is a correlation between cooling power and the amount of cooling capacity the compressor can provide. At the end of each control cycle, it is determined whether the cooling power can be adjusted. If the temperature inside the ultra-low temperature freezer is predicted to meet the required temperature, the cooling power can be appropriately reduced to balance cooling efficiency and energy consumption, optimizing energy utilization and maintaining a stable freezer temperature.

[0047] According to one embodiment of the present invention, a plurality of first temperature data and second temperature data can be detected in the current control cycle, which can be respectively composed of vectors or arrays. The temperature prediction model uses the input temperature data and cooling power data to change the temperature data in the current control cycle according to the current cooling power. When the first cooling power and the second cooling power remain unchanged, the temperature condition inside the cabinet of the freezer (second predicted temperature data) and the temperature condition inside the intermediate heat exchanger (first predicted temperature data) at the end of the next control cycle are predicted. The predicted temperature data can be used to adjust the cooling power of the first and second stage compressors in the next control cycle, thereby achieving precise control of the temperature inside the freezer. The temperature prediction model can be a deep learning neural network model, and the present invention does not limit the specific type of the temperature prediction model.

[0048] According to one embodiment of the present invention, a controller can evaluate and compare predicted temperature data, automatically determining whether to adjust cooling power. If the predicted temperature data meets certain conditions, the controller determines that the current cooling power can be adjusted. Depending on the specific situation, the cooling power of the primary and secondary compressors can be reduced, allowing the temperature inside the ultra-low temperature freezer to remain near the set point while saving energy.

[0049] According to one embodiment of the present invention, determining whether the first cooling power and the second cooling power meet a preset adjustment condition based on the first predicted temperature data and the second predicted temperature data includes: determining a first condition C1 and a second condition C2 according to formula (1),

[0050] Among them, T N，1，p is the first predicted temperature data in the intermediate heat exchanger at the end of the next control cycle, TN，2，p is the second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, T 1，max is the upper temperature limit of the intermediate heat exchanger, T 1，min is the lower limit of the temperature of the intermediate heat exchanger, T S is the set temperature inside the cabinet of the ultra-low temperature freezer, α is a preset coefficient greater than 1, and the first condition C1 and the second condition C2 are the adjustment conditions; when the first condition C1 and the second condition C2 are met at the same time, determine whether the first refrigeration power and the second refrigeration power meet the preset adjustment conditions.

[0051] According to one embodiment of the present invention, in the first condition of formula (1), T 1，min ≤T N，1，p ≤T 1，max This represents the range between the lower and upper temperature limits of the intermediate heat exchanger. This means that the first predicted temperature data within the intermediate heat exchanger at the end of the next control cycle must still be within this range. In other words, the temperature of the intermediate heat exchanger should not be too high or too low. If the temperature of the intermediate heat exchanger is too high, it will hinder the transfer of temperature from the ultra-low temperature freezer to the intermediate heat exchanger. In other words, if the temperature of the intermediate heat exchanger is too high, the secondary compressor will consume more power to transfer the temperature from the ultra-low temperature freezer to the intermediate heat exchanger. If the temperature of the intermediate heat exchanger is too low, the cooling power of the primary compressor will be too high, resulting in energy waste.

[0052] According to one embodiment of the present invention, in the second condition, T N，2，p ≤αT S The second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle is less than or equal to α times the set temperature inside the ultra-low temperature freezer. The preset coefficient is greater than 1. Therefore, the second predicted temperature is lower, meaning the cooling power is higher at this time. The first and second cooling powers can be reduced, thereby saving energy while maintaining the temperature inside the ultra-low temperature freezer near the set temperature.

[0053] In this way, the first condition and the second condition can be determined based on the actual requirements for the temperature of the intermediate heat exchanger and the cabinet body of the ultra-low temperature freezer. When the first condition and the second condition are met at the same time, it can be determined that the current refrigeration power is high, and the refrigeration power can be appropriately reduced, thereby saving energy and making the temperature control more precise.

[0054] According to one embodiment of the present invention, the temperature prediction model can be trained before use, and the training steps of the temperature prediction model include: obtaining first sample temperature data detected by the first temperature sensor and second sample temperature data detected by the second temperature sensor at multiple moments in the i-th historical control cycle, wherein i is a positive integer; obtaining the first sample refrigeration power of the first-stage compressor and the second sample refrigeration power of the second-stage compressor in the i+1-th historical control cycle; inputting the first sample temperature data and the second sample temperature data at multiple moments in the i-th historical control cycle, as well as the first sample refrigeration power and the second sample refrigeration power of the i+1-th historical control cycle into the temperature prediction model, and obtaining Obtain first predicted temperature data in the intermediate heat exchanger at multiple moments in the (i+1)th historical control cycle, and second predicted temperature data in the cabinet body of the ultra-low temperature freezer; determine a loss function of the temperature prediction model based on the first refrigeration power, the second refrigeration power, the first sample refrigeration power, the second sample refrigeration power, the first sample temperature data detected by the first temperature sensor at multiple moments in the (i+1)th historical control cycle, the second sample temperature data detected by the second temperature sensor, and the first predicted temperature data and the second predicted temperature data; train the temperature prediction model based on the loss function of the temperature prediction model to obtain a trained temperature prediction model.

[0055] According to one embodiment of the present invention, the historical control cycle is an actual cycle, and data at each moment can actually be collected. The temperature prediction model can predict the predicted temperature data for the (i+1)th historical control cycle based on the temperature data for the (i)th historical control cycle and the cooling power for the (i+1)th historical control cycle. This provides information on the temperature variations between the (i)th and (i+1)th historical control cycles. Lower temperatures require more cooling power. For example, a temperature change from -30°C to -40°C consumes less energy than a temperature change from -90°C to -100°C. Based on the relationship between temperature variation and cooling power, the temperature prediction model can predict the first and second predicted temperature data for the (i+1)th historical control cycle based on the first and second sample temperature data for the (i)th historical control cycle, as well as the first and second sample cooling power for the (i+1)th historical control cycle. A loss function is determined based on the difference between the first and second predicted temperature data and the measured first and second sample temperature data for the (i+1)th historical control cycle. Feedback adjustment of the loss function yields a trained temperature prediction model.

[0056] According to one embodiment of the present invention, determining the loss function of the temperature prediction model according to the first refrigeration power, the second refrigeration power, the first sample refrigeration power, the second sample refrigeration power, the first sample temperature data detected by the first temperature sensor at multiple moments in the i+1th historical control cycle, the second sample temperature data detected by the second temperature sensor, and the first predicted temperature data and the second predicted temperature data includes: determining the loss function L of the temperature prediction model according to formula (2): T ,

[0057] Wherein, P1 is the first cooling power, P 1，y is the first sample cooling power, P2 is the second cooling power, P 2，y The cooling power of the second sample, T i+1，1，j，d is the first sample temperature data at the jth moment of the i+1th historical control cycle, T i+1，1，j，p is the first predicted temperature data at the jth moment in the i+1th historical control cycle, T i+1，2，j，d is the second sample temperature data at the jth moment in the i+1th historical control cycle, T i+1，2，j，p is the second predicted temperature data at the jth moment in the (i+1)th historical control cycle, N is the number of moments in the control cycle, j≤N, and both j and N are positive integers.

[0058] According to one embodiment of the present invention, in formula (2), |T i+1，1，j，d -T i+1，1，j，p | is the absolute value of the difference between the first sample temperature data and the first predicted temperature data at the jth moment in the (i+1)th historical control cycle. This difference represents the error between the predicted temperature and the sample temperature. It represents the ratio between the jth moment and the total number of moments in the i+1th historical control period, and is used to reasonably weight the prediction errors at different moments in the loss function. The accuracy of the first predicted temperature data at the jth moment output by the temperature prediction model is usually higher than the accuracy of the first predicted temperature data at the j+1th moment. That is, the longer the time interval between the first predicted temperature data at a certain moment output by the temperature prediction model and the starting moment, the less accurate the prediction result. In order to improve the training efficiency, the higher the weight is set, the shorter the time interval with the starting moment, the more accurate the prediction result, and the lower the weight is set, so that higher weights can be given to items with lower accuracy, thereby improving the training intensity and training efficiency. This sums the temperature differences within the intermediate heat exchanger at each moment, multiplied by the corresponding weight. This sum represents the total of all temperature differences at all moments and is used to measure the degree of discrepancy between the predicted and actual temperatures over the entire historical control period. It is the ratio of the absolute value of the difference between the first refrigeration power and the first sample refrigeration power to the first refrigeration power. The ratio represents the relative error between the refrigeration power of the primary compressor in the current control period and the refrigeration power in the historical control period. Represents the similarity between the primary compressor's cooling power during the current control cycle and its cooling power during historical control cycles. To achieve the same cooling effect, lower temperatures require greater cooling power. Specifically, the closer the cooling power during the current control cycle is to that during historical control cycles, the closer the first sample temperature data is to the first temperature data during the current control cycle, the greater its reference value, and therefore, its weight. The product of these two terms represents the loss function for the temperature prediction model within the intermediate heat exchanger.

[0059] According to one embodiment of the present invention, in formula (2), |T i+1，2，j，d -T i+1，2，j，p | is the absolute value of the difference between the second sample temperature data and the second predicted temperature data at the jth moment in the (i+1)th historical control cycle. This difference represents the error between the second predicted temperature data and the actual temperature data. This sums the temperature differences within the ultra-low temperature freezer at each moment, multiplied by the corresponding weight. This sum represents the total of all temperature differences, and is used to measure the degree of discrepancy between the predicted and actual temperatures over the entire historical control period. The absolute value of the difference between the second refrigeration power and the second sample refrigeration power is the ratio of the second refrigeration power. This ratio represents the relative error between the refrigeration power of the secondary compressor in the current control cycle and the refrigeration power in the historical control cycle. Represents the similarity between the secondary compressor's cooling power during the current control cycle and its cooling power during historical control cycles. To achieve the same cooling effect, lower temperatures require greater cooling power. Specifically, the closer the cooling power during the current control cycle is to that during historical control cycles, the closer the second sample temperature data is to the second temperature data during the current control cycle, the greater its reference value, and therefore, its weight. The product of these two terms represents the loss function for the temperature prediction model within the ultra-low temperature freezer.

[0060] According to one embodiment of the present invention, the sum of the two aforementioned terms represents the loss function of the temperature prediction model. During the training of the temperature prediction model, the loss function is back-propagated and some parameters within the model are adjusted to reduce the value of the loss function, thereby improving the accuracy of the temperature prediction model and obtaining a trained temperature prediction model.

[0061] In this way, during the training process, the difference between the sample temperature data and the predicted temperature data can be determined, and weights can be set based on the characteristics that the shorter the time interval with the start moment, the higher the accuracy, and the closer the current control cycle cooling power is to the historical control cycle cooling power, the closer the temperature is, and the greater the reference value of the temperature error. The weighted summation of the j-th moment temperature error output by the temperature prediction model at each moment is performed to obtain a loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the temperature prediction model.

[0062] According to one embodiment of the present invention, the temperature prediction model is a neural network model, and the power setting model is an optimization model. If the cooling power needs to be adjusted, the system calculates the adjusted first cooling power for the primary compressor and the adjusted second cooling power for the secondary compressor for the next control cycle based on the calculation results of the temperature prediction model and the power setting model.

[0063] According to one embodiment of the present invention, if the first cooling power and the second cooling power meet the preset adjustment conditions, the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle are obtained based on the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model and the power setting model, including: obtaining the constraints of the power setting model based on the first temperature data, the second temperature data, the first cooling power, the second cooling power and the temperature prediction model; obtaining the objective function of the power setting model based on the first temperature data, the second temperature data and the temperature prediction model; and obtaining the adjusted first cooling power and the adjusted second cooling power based on the constraints and the objective function.

[0064] According to one embodiment of the present invention, constraints may include temperature ranges, cooling power limits, and other constraints, which are used to constrain the system's operating behavior and the value ranges of various parameters during the optimization process. An objective function describes the optimization goal. Based on the constraints and the optimal solution to the objective function, the optimal cooling power solution (i.e., the adjusted first cooling power and the adjusted second cooling power) is obtained.

[0065] According to one embodiment of the present invention, obtaining the constraint conditions of the power setting model based on the first temperature data, the second temperature data, the first cooling power, the second cooling power, and the temperature prediction model includes: obtaining the constraint conditions of the power setting model according to the following formula: P'1+P'2<P1+P2 (5)

[0066] T 1，min ≤f N，1 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2 ), P'1, P'2]≤T 1，max (6) f N，2 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2 ), P'1, P'2]≤βT S (7)

[0067] Wherein, P'1 is the first cooling power after adjustment to be determined, P1 is the first cooling power, P'2 is the second cooling power after adjustment to be determined, P2 is the second cooling power, T 1，1 is the first temperature data at the first moment of the current control cycle, T 2，1 is the first temperature data at the second moment of the current control cycle, T N，1 is the first temperature data at the Nth moment of the current control cycle, T 1，2 is the second temperature data at the first moment of the current control cycle, T 2，2 is the second temperature data at the second moment of the current control cycle, T N，2 is the second temperature data at the Nth moment of the current control cycle, f is the temperature prediction model, and f N，1 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2 ), P'1, P'2] is the predicted temperature in the intermediate heat exchanger at the end of the next control cycle determined by the temperature prediction model based on the first temperature data, the second temperature data, the first cooling power to be adjusted and the second cooling power to be adjusted, f N，2 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2), P'1, P'2] is the predicted temperature inside the ultra-low temperature freezer at the end of the next control cycle determined by the temperature prediction model based on the first temperature data, the second temperature data, the first cooling power to be adjusted, and the second cooling power to be adjusted, T 1，max is the upper temperature limit of the intermediate heat exchanger, T 1，min is the lower limit of the temperature of the intermediate heat exchanger, T S is the set temperature inside the ultra-low temperature freezer, and β is a preset coefficient less than 1.

[0068] According to one embodiment of the present invention, in formula (3), f N，1 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2 ), P'1, P'2] = T N，1，p Indicates the first predicted temperature data in the intermediate heat exchanger at the end time of the next control cycle. N，2 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2 ), P'1, P'2] = T N，2，p The second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle. N，1 -T 1，1 is the temperature change in the intermediate heat exchanger during the current control period. Since the cold storage cabinet has a good thermal insulation effect, it can be considered that the temperature drop rate in the intermediate heat exchanger during the current control period is linearly positively correlated with the first cooling power, that is, it is proportional to the first cooling power P1. Moreover, the greater the second cooling power, the more heat is dissipated from the cabinet of the ultra-low temperature cold storage cabinet to the intermediate heat exchanger, making the temperature change in the intermediate heat exchanger slower, that is, T N，1 -T 1，1 is inversely proportional to the second cooling power P2, therefore, T N，1 -T 1，1 and There is a correlation. Taking the Nth moment of the current control cycle as the 1st moment of the next control cycle, based on the same inference, T N，1，p -T N，1 and There is a correlation. And, since the temperatures are close, it can be considered that T N，1 -T 1，1 and The correlation coefficient with TN，1，p -T N，1 and The correlation coefficients are close or equal, so and The ratio between them is equal to T N，1，p -T N，1 With T N，1 -T 1，1 The ratio between them.

[0069] According to one embodiment of the present invention, T N，2 -T 1，2 is the temperature change inside the ultra-low temperature freezer in the current control cycle, which is proportional to the second refrigeration power P2. Moreover, the higher the temperature inside the intermediate heat exchanger, the slower the temperature change inside the ultra-low temperature freezer. Therefore, T N，2 -T 1，2 The average temperature in the intermediate heat exchanger Inversely proportional, therefore, T N，2 -T 1，2 and There is a correlation between them. Similarly, T N，2，p -T N，2 and There is a correlation between them. And T N，2 -T 1，2 and The correlation coefficient between N，2，p -T N，2 and The correlation coefficients between them are close or equal, that is, and The ratio between them is equal to T N，2，p -T N，2 With T N，2 -T 1，2 The ratio between them.

[0070] According to one embodiment of the present invention, based on the above relationship, formulas (3) and (4) can be obtained to obtain the undetermined adjusted first cooling power and the undetermined adjusted second cooling power. This formula can separately separate the undetermined adjusted first cooling power and the undetermined adjusted second cooling power to be determined, making it easier to solve the adjusted first cooling power and the adjusted second cooling power.

[0071] According to one embodiment of the present invention, in formula (5), the sum of the to-be-determined adjusted first cooling power and the to-be-determined adjusted second cooling power is made smaller than the sum of the first cooling power and the second cooling power, thereby achieving the purpose of saving energy.

[0072] According to one embodiment of the present invention, in formula (6), after the cooling power is adjusted, the predicted temperature in the intermediate heat exchanger is within a set temperature range. This constraint ensures that the adjusted cooling power can maintain the temperature in the intermediate heat exchanger within the set range, thus achieving the temperature control requirement.

[0073] According to one embodiment of the present invention, in formula (7), after the refrigeration power is adjusted, the predicted temperature inside the cabinet of the ultra-low temperature freezer is less than or equal to the set ultra-low temperature freezer temperature multiplied by a preset coefficient. Wherein, the preset coefficient is less than 1, which can appropriately increase the temperature and keep it near the set temperature, and reduce the refrigeration power to achieve the purpose of energy saving. This constraint condition enables the adjusted refrigeration power to maintain the temperature of the ultra-low temperature freezer near the set temperature to meet the refrigeration demand. All of the above constraints can constitute the constraints of the power setting model, that is, the constraints satisfied when solving the adjusted first refrigeration power and the adjusted second refrigeration power.

[0074] This approach ensures that the adjusted primary and secondary cooling power are within appropriate ranges, based on current temperature data and the output of the prediction model. This reduces overcooling and energy consumption. The adjusted predicted temperature within the intermediate heat exchanger is within the set temperature range, allowing the refrigeration system to maintain temperature control requirements and reduce overheating or underheating. The adjusted predicted temperature within the ultra-low temperature freezer is equal to or less than the set ultra-low temperature freezer temperature multiplied by a preset coefficient, meeting refrigeration requirements and reducing the risk of refrigerated goods spoiling due to overheating. This improves the stability, efficiency, and temperature control capabilities of the refrigeration system, providing reliable cooling and refrigeration functions.

[0075] According to one embodiment of the present invention, obtaining the objective function of the power setting model based on the first temperature data, the second temperature data and the temperature prediction model includes: obtaining the objective function of the power setting model according to formulas (8) and (9). min(P'1+P'2) (8) min|f N，2 [(T 1，1 , T 2，1 ...T N，1 ), (T 1，2 , T 2，2 ...T N，2 ), P'1, P'2]-T S (9)

[0076] According to one embodiment of the present invention, in formula (8), the objective function represents minimizing the sum of the adjusted primary and secondary refrigeration powers. In formula (9), the objective function represents minimizing the absolute difference between the predicted temperature and the set temperature within the ultra-low temperature freezer after adjustment. By minimizing this difference, the power of the ultra-low temperature freezer can be minimized, and the temperature can be precisely controlled.

[0077] In this way, the cooling power can be adjusted to the minimum. By minimizing the power, the goals of energy efficiency optimization and energy conservation and emission reduction can be achieved. Minimizing the cooling power can reduce the energy consumption of the equipment and provide more efficient refrigeration system operation while maintaining the cooling effect.

[0078] According to one embodiment of the present invention, an optimization solution is performed based on the objective function and constraints of the above power setting model. For example, the optimization solution can be performed through methods such as nonlinear programming and genetic algorithms to obtain the optimal solution of the to-be-determined adjusted first cooling power and the to-be-determined adjusted second cooling power as the adjusted first cooling power and the adjusted second cooling power.

[0079] According to one embodiment of the present invention, at the start of the next control cycle, the cooling power of the first compressor can be set to the adjusted first cooling power, while the cooling power of the second compressor can be set to the adjusted second cooling power. This reduces energy consumption while ensuring cooling efficiency during the next control cycle.

[0080] According to an embodiment of the present invention, an ultra-low temperature freezer uses two temperature sensors to detect temperature data from the intermediate heat exchanger and the interior of the freezer, respectively, enabling precise control of the freezer's internal temperature. This precise control is crucial for applications requiring ultra-low temperatures, such as biomedical research. The cooling power of the primary and secondary compressors is adjusted using a temperature prediction model and a power setting model, thereby achieving control over the freezer's temperature stability and power accuracy, and effectively utilizing energy. A controller determines whether cooling power adjustment is necessary based on preset adjustment conditions, thereby reducing the cooling power of the primary and secondary compressors while maintaining temperature requirements, minimizing energy consumption. When determining whether cooling power adjustment is appropriate for the next control cycle, a first condition and a second condition are determined based on the actual temperature requirements of the intermediate heat exchanger and the interior of the ultra-low temperature freezer. If both the first and second conditions are met, the current cooling power is determined to be high, and the cooling power can be appropriately reduced, thereby conserving energy and achieving more precise temperature control. When training the temperature prediction model, the difference between sample temperature data and predicted temperature data can be determined. Weights are set based on the principle that shorter time intervals from the start time yield higher accuracy, and that the closer the cooling power in the current control cycle is to the cooling power in the historical control cycle, the closer the temperature is, and the greater the reference value of the temperature error. A weighted summation of the j-th temperature error output by the temperature prediction model at each moment is then performed to obtain a loss function. This improves the accuracy and objectivity of the loss function, thereby increasing training efficiency and the accuracy of the temperature prediction model. When determining the constraints for the power setting model, the adjusted primary and secondary cooling powers can be kept within an appropriate range. This calculation, based on the current temperature data and the output of the prediction model, can reduce overcooling and energy consumption. The adjusted predicted temperature within the intermediate heat exchanger is within the set temperature range, allowing the refrigeration system to maintain temperature control requirements and reducing overheating or underheating. The adjusted predicted temperature within the ultra-low temperature freezer is less than or equal to the set ultra-low temperature freezer temperature multiplied by a preset coefficient, meeting refrigeration requirements and reducing the risk of refrigerated items deteriorating due to overheating. This improves the stability, efficiency, and temperature control capabilities of the refrigeration system, providing reliable cooling and refrigeration capabilities. When determining the objective function of the power setting model, the cooling power can be adjusted to the minimum. By minimizing power, energy efficiency optimization and energy conservation and emission reduction can be achieved. Minimizing cooling power reduces equipment energy consumption and provides more efficient refrigeration system operation while maintaining cooling performance.

[0081] FIG2 exemplarily shows a flow chart of a method for controlling energy-saving operation of an ultra-low temperature freezer according to an embodiment of the present invention. The method comprises:

[0082] Step S101, acquiring first temperature data detected by a first temperature sensor and second temperature data detected by a second temperature sensor at multiple moments in a current control cycle;

[0083] Step S102, determining a first refrigeration power of the first-stage compressor and a second refrigeration power of the second-stage compressor in the current control cycle;

[0084] Step S103: Inputting the first temperature data, the second temperature data, the first cooling power, and the second cooling power into a temperature prediction model to obtain second predicted temperature data inside the ultra-low temperature freezer and first predicted temperature data inside the intermediate heat exchanger at the end of the next control cycle.

[0085] Step S104: determining whether the first cooling power and the second cooling power meet a preset adjustment condition based on the first predicted temperature data and the second predicted temperature data;

[0086] Step S105: If the first cooling power and the second cooling power meet the preset adjustment conditions, then obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle based on the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model;

[0087] Step S106: at the start of the next control cycle, the cooling power of the first-stage compressor is set to the adjusted first cooling power, and the cooling power of the second-stage compressor is set to the adjusted second cooling power.

[0088] Those skilled in the art will appreciate that the embodiments of the present invention described above and shown in the accompanying drawings are intended to be illustrative only and are not intended to limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and illustrated in the embodiments. Any variations or modifications may be made to the embodiments of the present invention without departing from the principles described.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An ultra-low temperature freezer, characterized in that: include: Temperature sensor group, primary compressor, secondary compressor, intermediate heat exchanger and controller; The temperature sensor group includes a first temperature sensor and a second temperature sensor, wherein the first temperature sensor is used to detect first temperature data in the intermediate heat exchanger, and the second temperature sensor is used to detect second temperature data in the cabinet of the ultra-low temperature freezer; The primary compressor is used to cool the intermediate heat exchanger; The secondary compressor is used to cool the space inside the ultra-low temperature freezer and transfer the heat to the intermediate heat exchanger; The controller is used to: At multiple moments in the current control cycle, respectively acquiring first temperature data detected by the first temperature sensor and second temperature data detected by the second temperature sensor; determining a first refrigeration power of the primary compressor and a second refrigeration power of the secondary compressor in a current control cycle; Inputting the first temperature data, the second temperature data, the first refrigeration power, and the second refrigeration power into a temperature prediction model to obtain second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, and first predicted temperature data inside the intermediate heat exchanger; determining, based on the first predicted temperature data and the second predicted temperature data, whether the first cooling power and the second cooling power meet a preset adjustment condition; If the first cooling power and the second cooling power meet the preset adjustment conditions, then obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model; At the start of the next control cycle, the refrigeration power of the first-stage compressor is set to the adjusted first refrigeration power, and the refrigeration power of the second-stage compressor is set to the adjusted second refrigeration power.

2. The ultra-low temperature freezer according to claim 1, characterized in that: Determining whether the first cooling power and the second cooling power meet a preset adjustment condition according to the first predicted temperature data and the second predicted temperature data includes: According to the formula Determine the first condition C1 and the second condition C2, where T N，1，p is the first predicted temperature data in the intermediate heat exchanger at the end of the next control cycle, T N，2，p is the second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, T 1，max is the upper temperature limit of the intermediate heat exchanger, T 1，min is the lower limit of the temperature of the intermediate heat exchanger, T S is the set temperature inside the ultra-low temperature freezer, α is a preset coefficient greater than 1, and the first condition C1 and the second condition C2 are the adjustment conditions; When the first condition C1 and the second condition C2 are satisfied at the same time, it is determined whether the first refrigeration power and the second refrigeration power meet a preset adjustment condition.

3. The ultra-low temperature freezer according to claim 1, characterized in that: The training steps of the temperature prediction model include: At multiple moments in the i-th historical control cycle, first sample temperature data detected by the first temperature sensor and second sample temperature data detected by the second temperature sensor are acquired, where i is a positive integer; Obtaining a first sample refrigeration power of the first-stage compressor and a second sample refrigeration power of the second-stage compressor in the (i+1)th historical control period; Inputting the first sample temperature data and the second sample temperature data at multiple moments in the i-th historical control period, and the first sample refrigeration power and the second sample refrigeration power at the i+1-th historical control period into the temperature prediction model, obtaining first predicted temperature data in the intermediate heat exchanger at multiple moments in the i+1-th historical control period, and second predicted temperature data in the cabinet of the ultra-low temperature freezer; determining a loss function of the temperature prediction model according to the first cooling power, the second cooling power, the first sample cooling power, the second sample cooling power, first sample temperature data detected by the first temperature sensor at multiple moments in the (i+1)th historical control cycle, second sample temperature data detected by the second temperature sensor, the first predicted temperature data, and the second predicted temperature data; The temperature prediction model is trained according to the loss function of the temperature prediction model to obtain a trained temperature prediction model.

4. The ultra-low temperature freezer according to claim 3, characterized in that: Determining a loss function of the temperature prediction model based on the first cooling power, the second cooling power, the first sample cooling power, the second sample cooling power, first sample temperature data detected by the first temperature sensor at multiple moments in the (i+1)th historical control cycle, second sample temperature data detected by the second temperature sensor, and the first predicted temperature data and the second predicted temperature data, including: According to the formula Determine the loss function L of the temperature prediction model T , where P1 is the first cooling power, P 1，y is the first sample cooling power, P2 is the second cooling power, P 2，y The cooling power of the second sample, T i+1，1，j，d is the first sample temperature data at the jth moment of the i+1th historical control cycle, T i+1，1，j，p is the first predicted temperature data at the jth moment in the i+1th historical control cycle, T i+1，2，j，d is the second sample temperature data at the jth moment in the i+1th historical control cycle, T i+1，2，j，p is the second predicted temperature data at the jth moment in the (i+1)th historical control cycle, N is the number of moments in the control cycle, j≤N, and both j and N are positive integers.

5. The ultra-low temperature freezer according to claim 1, characterized in that: If the first cooling power and the second cooling power meet the preset adjustment conditions, obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model, including: Obtaining constraints of a power setting model according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, and the temperature prediction model; obtaining an objective function of a power setting model according to the first temperature data, the second temperature data, and the temperature prediction model; The adjusted first refrigeration power and the adjusted second refrigeration power are obtained according to the constraint condition and the objective function.

6. The ultra-low temperature freezer according to claim 5, characterized in that: Obtaining constraints of a power setting model according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, and the temperature prediction model includes: According to the formula P'1+P'2<P1+P2 T 1,min ≤f N，1 [(T 1，1 ,T 2，1 …T N，1 ),(T 1，2 ,T 2，2 …T N，2 ),P’1,P’2]≤T 1,max f N，2 [(T 1，1 ,T 2，1 …T N，1 ),(T 1，2 ,T 2，2 …T N，2 ),P’1,P’2]≤βT S Obtain the constraints of the power setting model, where P'1 is the first cooling power after adjustment to be determined, P1 is the first cooling power, P'2 is the second cooling power after adjustment to be determined, and P2 is the second cooling power. Power, T 1，1 is the first temperature data at the first moment of the current control cycle, T 2，1 is the first temperature data at the second moment of the current control cycle, T N，1 is the first temperature data at the Nth moment of the current control cycle, T 1，2 is the second temperature data at the first moment of the current control cycle, T 2，2 is the second temperature data at the second moment of the current control cycle, T N，2 is the second temperature data at the Nth moment of the current control cycle, f is the temperature prediction model, and f N，1 [(T 1，1 , T 2，1 …T N，1 ),(T 1，2 ,T 2，2 …T N，2 ), P'1, P'2] is the predicted temperature in the intermediate heat exchanger at the end of the next control cycle determined by the temperature prediction model based on the first temperature data, the second temperature data, the first cooling power to be adjusted and the second cooling power to be adjusted, f N，2 [(T 1，1 , T 2，1 …T N，1 ), (T 1，2 , T 2，2 …T N，2 ), P'1, P'2] is the predicted temperature inside the ultra-low temperature freezer at the end of the next control cycle determined by the temperature prediction model based on the first temperature data, the second temperature data, the to-be-determined adjusted first refrigeration power and the to-be-determined adjusted second refrigeration power, T 1，max is the upper temperature limit of the intermediate heat exchanger, T 1，min is the lower limit of the temperature of the intermediate heat exchanger, T S is the set temperature inside the ultra-low temperature freezer, and β is a preset coefficient less than 1.

7. The ultra-low temperature freezer according to claim 6, characterized in that: Obtaining an objective function of a power setting model according to the first temperature data, the second temperature data, and the temperature prediction model, including: According to the formula min(P'1+P'2) min|f N，2 [(T 1，1 ,T 2，1 …T N，1 ),(T 1，2 ,T 2，2 …T N，2 ),P’1,P’2]-T S | Obtain the objective function of the power setting model.

8. A method for controlling energy-saving operation of an ultra-low temperature freezer, characterized in that: The method is used for a controller of an ultra-low temperature freezer according to any one of claims 1 to 7, comprising: At multiple moments in the current control cycle, the first temperature detected by the first temperature sensor is obtained respectively. temperature data, and second temperature data detected by a second temperature sensor; determining a first refrigeration power of the primary compressor and a second refrigeration power of the secondary compressor in a current control cycle; Inputting the first temperature data, the second temperature data, the first refrigeration power, and the second refrigeration power into a temperature prediction model to obtain second predicted temperature data inside the ultra-low temperature freezer at the end of the next control cycle, and first predicted temperature data inside the intermediate heat exchanger; determining, based on the first predicted temperature data and the second predicted temperature data, whether the first cooling power and the second cooling power meet a preset adjustment condition; If the first cooling power and the second cooling power meet the preset adjustment conditions, then obtaining the adjusted first cooling power of the first-stage compressor and the adjusted second cooling power of the second-stage compressor for the next control cycle according to the first temperature data, the second temperature data, the first cooling power, the second cooling power, the temperature prediction model, and the power setting model; At the start of the next control cycle, the refrigeration power of the first-stage compressor is set to the adjusted first refrigeration power, and the refrigeration power of the second-stage compressor is set to the adjusted second refrigeration power.

Images