A refrigeration room energy-saving monitoring system and method based on artificial intelligence

Abstract

The present invention discloses an energy-saving supervision system and method for a refrigeration room based on artificial intelligence, and relates to the field of energy-saving supervision. The system is composed of a preprocessing module, a regional control module, a detection module, a data processing module, an analysis module, and an execution module. The output end of the regional control module is electrically connected to the input end of the data processing module; the output end of the detection module is electrically connected to the input end of the data processing module; the output end of the data processing module is electrically connected to the input end of the analysis module; the output end of the analysis module is electrically connected to the input end of the execution module; the output end of the execution module is electrically connected to the regional control module and the data processing module; the present invention aims to divide the refrigeration room system into regions under the environment background of large temperature difference between day and night, and supervise the energy consumption in each region, and select reasonable regional work allocation in different time periods to achieve the effect of reducing energy consumption.

Description

Technical Field

[0001] The present invention belongs to the field of energy-saving supervision and relates to artificial intelligence technology, and specifically to an energy-saving supervision system and method for a refrigeration room based on artificial intelligence. Background Art

[0002] The refrigeration room lowers the indoor temperature through a cycle of compressing refrigerant, condensing refrigerant, expanding refrigerant, and evaporating refrigerant, thereby achieving a cooling effect to maintain operational requirements. During the refrigeration process, the supply temperature of cooling water and chilled water will greatly affect the energy consumption of the entire chilled water system.

[0003] In the actual production and operation process, the traditional industrial refrigeration room system usually makes extensive adjustments to the local energy of each unit directly through the central control console in order to achieve the minimum demand for terminal refrigeration. For example, a fixed value and deviation working range are set for the cooling water temperature of the chilled water system of the refrigeration unit, and the system automatically operates within the range. In some parts of my country, due to geographical environmental problems, the temperature difference between day and night is too large. Although this extensive adjustment can achieve the ultimate demand effect of refrigeration and constant temperature, in actual production, this extensive adjustment cannot adapt well to such a large temperature difference change, and is often accompanied by the phenomenon of excessive cooling, resulting in excessive energy consumption of the building and failing to achieve the expected effect of ideal energy saving. Summary of the invention

[0004] The purpose of the present invention is to provide an artificial intelligence-based refrigeration room energy-saving monitoring system and method to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an artificial intelligence-based refrigeration room energy-saving supervision method, the method comprising the following steps:

[0006] Step S1, collecting performance data of refrigeration room units, building a refrigeration room history database, analyzing the data in the refrigeration room history database, dividing the refrigeration room units in the working area into two areas, and performing zoning management on the two areas;

[0007] Step S2, dividing the two time stages by detecting the extreme values ​​of the day and night temperature changes in the working area and the duration at the corresponding temperature;

[0008] Step S3, constructing an algorithm model, and obtaining the capacity coefficients of the two areas in the time period through various values ​​of the refrigeration room units and the corresponding output power and corresponding energy consumption;

[0009] Step S4: select the best regional working mode and energy-saving mode in two time periods according to the capacity coefficient obtained by the algorithm model, and adjust the energy-saving mode according to the loss of the refrigeration room units in the two areas.

[0010] According to the above technical solution, in step S1, the performance data includes the energy consumption data WH of the refrigeration room, the refrigeration data CH and the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit. q , Chilled water temperature T d , ambient temperature T;

[0011] According to the energy consumption data WH and refrigeration data CH of the refrigeration room unit, the capacity coefficient P of the refrigeration room unit is calculated. The refrigeration room units in the working area are divided into regions according to the obtained capacity coefficients, so that the capacity coefficients of Area 1 and Area 2 are equal, that is: P Y1 =P Y2 , where the number of units in the region Y1 + the number of units in the region Y2 = the total number of units in the region Y, the regional total capacity coefficient P y =P Y1 +P Y2 .

[0012] According to the above technical solution, in step S2, by monitoring t n The temperature changes in the area are recorded, and the temperature change data is obtained to obtain the extreme value T of the temperature change in the area. max 、T min and the time t at the corresponding temperature Tmax ,t Tmin , and the corresponding time point T a 、T b 、T c 、T d , divided out at t n High temperature stage h and low temperature stage c .

[0013] According to the above technical solution, in step S3, the process of building the algorithm model is:

[0014] Detect the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit q , Chilled water temperature T d , ambient temperature T, and store the data;

[0015] By combining the linear regression equation:

[0016] P n=β0+β1T+β2T q +β3T d +ε,

[0017] Among them, β0, β1, β2, β3 represent regression coefficients; ε represents the constant term; it can be obtained that in the high temperature stage h and low temperature stage c The required capacity factor P n ;

[0018] The minimum capacity coefficient P of Area 1 and Area 2 min Set as the capacity coefficient threshold in the region, by comparing the capacity coefficient P in the region with the minimum capacity coefficient P min The relationship between the regional capacity coefficient P> the minimum capacity coefficient P min When the regional working mode is performance mode, when the capacity coefficient P in the region = the minimum capacity coefficient P min At this time, the regional working mode is energy-saving mode.

[0019] According to the above technical solution, in step S4, the best regional working mode in the stage is:

[0020] In the high temperature stage h In this case, both Area 1 and Area 2 work in performance mode, and the total capacity coefficient P in the area y Meet the high temperature stage h The required capacity factor P n Under the condition of n Data set, extract the capacity coefficient P in the set y The minimum value is obtained, and the corresponding capacity coefficients of Area 1 and Area 2 and the corresponding fan, water pump, and compressor data are obtained, and finally the performance data of the refrigeration room unit is output;

[0021] In the low temperature stage c Under this circumstance, the working mode of Area 1 and Area 2 needs to output the performance data of the refrigeration room units after comparing the results of the optimal capacity output. The specific process is as follows:

[0022] Set the energy-saving mode in Area 1 and Area 2 as the first priority, and determine the total capacity coefficient P in the area at this time. y Whether it meets the low temperature stage c The required capacity factor P n ;

[0023] When the conditions are met, the performance data of the refrigeration room unit is output;

[0024] At this time, the total capacity coefficient P in the region y Does not meet the low temperature stage c The required capacity factor P n When setting the second priority: the capacity coefficient P in Area 1 Y1 and the capacity coefficient P of Area 2 Y2 Find the total capacity coefficient P in the region within the data range y The largest matching object outputs the performance data of the refrigeration room unit and determines the capacity coefficient P of Area 1 under the output conditions at this time. Y1 and the capacity coefficient P of Area 2 Y2 size;

[0025] When the capacity coefficient P of Area 1 Y1 Greater than the capacity coefficient P of Area 2 Y2 When , it is energy saving mode A;

[0026] When the capacity coefficient P of Area 2 Y2 Greater than the capacity coefficient P of Area 1 Y1 When , it is energy saving mode B;

[0027] The time thresholds of energy-saving mode A and energy-saving mode B are both set to t m , start timing when it is determined that the working modes of Area 1 and Area 2 are both in energy-saving mode and the conditions are not met, and record the energy-saving mode at this time. When the time threshold is reached, determine the working area mode at this time and change the energy-saving mode. The specific process is as follows:

[0028] If in t m At the beginning, it is in energy-saving mode A, that is, the capacity coefficient of Area 1 is P Y1 Greater than the capacity coefficient P of Area 2 Y2 , then at t m At the end, it switches to energy-saving mode B, that is, the capacity coefficient P of Area 2 Y2 Greater than the capacity coefficient P of Area 1 Y1 .

[0029] By detecting the original efficiency η of the refrigeration room unit and the current efficiency η0 of the refrigeration room unit, the loss rate of the refrigeration room unit is calculated. The calculation formula is:

[0030]

[0031] The overall loss level of Area 1 is:

[0032]

[0033] The overall loss level of Area2 is:

[0034]

[0035] ω i Expressed as the loss rate of the i-th device;

[0036] Changing the time thresholds of energy-saving mode A and energy-saving mode B according to the overall loss level of the area;

[0037] When ω1>ω2, the time threshold of energy-saving mode A is reduced according to the loss ratio.

[0038]

[0039] When ω1<ω2, the time threshold of the energy-saving mode B state is reduced according to the loss degree ratio.

[0040]

[0041] According to the degree of loss, the time t m Change to t m1 or m2 .

[0042] The supervision system of the refrigeration room energy-saving supervision method based on artificial intelligence is characterized in that the system includes: a preprocessing module, a regional control module, a detection module, a data processing module, an analysis module and an execution module;

[0043] The pre-processing module is used to construct a historical database of refrigeration rooms and divide the refrigeration room units in the area into regions based on historical data;

[0044] The regional control module performs zone-merging management on the divided areas, and uniformly sets the values ​​of the refrigeration room units in the area according to the capacity requirements;

[0045] The detection module is used to detect various environmental values ​​in the target terminal space, various input and output values ​​of the refrigeration room unit, and the extreme values ​​and corresponding time points of the day and night temperature changes in the working area;

[0046] The data processing module is used to receive feedback data from the detection module and save various feedback data; the analysis module analyzes the best regional working mode based on the algorithm model and the capacity optimization setting results;

[0047] The execution module is used to receive the optimal regional working mode finally analyzed by the analysis module, and transmit the corresponding data to the regional control module to adjust the refrigeration room unit;

[0048] The output end of the preprocessing module is electrically connected to the input end of the regional control module; the output end of the regional control module is electrically connected to the input end of the data processing module; the output end of the detection module is electrically connected to the input end of the data processing module; the output end of the data processing module is electrically connected to the input end of the analysis module; the output end of the analysis module is electrically connected to the input end of the execution module; the execution module is electrically connected to the regional control module and the data processing module, and the detection module and the analysis module are electrically connected.

[0049] The detection module includes a sensor unit and a stage unit; the sensor unit detects the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit. q , Chilled water temperature T d , ambient temperature T, and set stage data storage; the stage unit monitors t in the working area n The temperature change in the area is recorded, and the temperature change data is obtained to obtain the extreme value of the temperature change in the area and the corresponding time point, and the area is divided into n High temperature stage h and low temperature stage c ; and set and record the energy-saving mode stage time in the energy-saving mode state.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention aims to divide the refrigeration room system into areas under the environment background of large temperature difference between day and night, and supervise the energy consumption in each area and the performance data of the refrigeration room unit, analyze the best regional working mode through model in different time periods, adjust the energy-saving mode of each area on the premise of meeting the production capacity requirements, and change the unit output time by monitoring the unit loss degree, so as to effectively reduce the energy consumption of the refrigeration room system and reduce human resource investment. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0052] Figure 1 It is a schematic diagram of the structure of the present invention; DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 The present invention provides a technical solution: an artificial intelligence-based refrigeration room energy-saving supervision method, the method comprising:

[0055] Collect performance data of refrigeration room units, build a refrigeration room history database, and analyze the data in the refrigeration room history database, wherein the performance data includes energy consumption data WH, refrigeration data CH, and performance data of fans, water pumps, and compressors in the refrigeration room units, as well as cooling water temperature, chilled water temperature, and ambient temperature;

[0056] According to the energy consumption data WH and refrigeration data CH of the refrigeration room unit, the capacity coefficient P of the refrigeration room unit is calculated. The refrigeration room units in the working area are divided into regions according to the obtained capacity coefficients, so that the capacity coefficients of Area 1 and Area 2 are equal, that is: P Y1 =P Y2 , where the number of units in the region Y1 + the number of units in the region Y2 = the total number of units in the region Y, the regional total capacity coefficient:

[0057] P y =P Y1 +P Y2 .

[0058] For example, there are 42 refrigeration room units in the working area. We collect all the performance data of these refrigeration room units through the preprocessing module to calculate the energy consumption data WH and cooling data CH corresponding to each unit, and then we can get the capacity coefficient P of each of the 42 refrigeration room units; group the 42 refrigeration room units according to the capacity coefficient, so that the total capacity coefficients of the refrigeration room units in the two areas are equal, that is, Y1 = 19, Y2 = 23, so that P Y1 =P Y2 .

[0059] By monitoring the working area n The temperature changes in the area are recorded, and the temperature change data is obtained to obtain the extreme value T of the temperature change in the area. max 、T min and the time t at the corresponding temperature Tmax ,t Tmin , and the corresponding time point T a、T b 、T c 、T d , and divide it into n High temperature stage h and low temperature stage c .

[0060] For example, the highest temperature in 48 hours is 38℃, starting from 11:00 and ending at 17:00, and lasting for 6 hours, which is the high temperature stage. h :T a ~T b , where time point T a is 11:00, time point T b is 17:00, the temperature is t Tmax The lowest temperature is -5℃, starting from 0:00 and ending at 8:00, and lasting for 8 hours, which is the low temperature stage. c :T c ~T d The time point T c is 0:00, time point T d is 8:00, and the temperature is t Tmax 8h;

[0061] An algorithm model is constructed, and the capacity coefficients of the two areas in the time period are obtained through the various values ​​of the refrigeration room units and the corresponding output power and corresponding energy consumption; the process of constructing the algorithm model is:

[0062] Detect the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit q , Chilled water temperature T d , ambient temperature T, and store the data;

[0063] By combining the linear regression equation:

[0064] P n =β0+β1T+β2T q +β3T d +ε,

[0065] Among them, β0, β1, β2, β3 represent regression coefficients; ε represents the constant term; it can be obtained that in the high temperature stage h and low temperature stage c The required capacity factor P n ;

[0066] The minimum capacity coefficient P of Area 1 and Area 2 minSet as the capacity coefficient threshold in the region, by comparing the capacity coefficient P in the region with the minimum capacity coefficient P min The relationship between the regional capacity coefficient P> the minimum capacity coefficient P min When the regional working mode is performance mode, when the capacity coefficient P in the region = the minimum capacity coefficient P min At this time, the regional working mode is energy-saving mode.

[0067] The capacity coefficient obtained by the algorithm model is used to select the best regional working mode and energy-saving mode in the two time periods according to the capacity coefficient, and the energy-saving mode is adjusted according to the loss of the refrigeration room units in the two areas:

[0068] Best regional working method within the stage:

[0069] In the high temperature stage h In this case, both Area 1 and Area 2 work in performance mode, and the total capacity coefficient P in the area y Meet the high temperature stage h The required capacity factor P n Under the condition of n Data set, extract the capacity coefficient P in the set y The minimum value is obtained, and the corresponding capacity coefficients of Area 1 and Area 2 and the corresponding fan, water pump, and compressor data are obtained, and finally the performance data of the refrigeration room unit is output;

[0070] In the low temperature stage c Under this circumstance, the working mode of Area 1 and Area 2 needs to output the performance data of the refrigeration room units after comparing the results of the optimal capacity output. The specific process is as follows:

[0071] Set the energy-saving mode in Area 1 and Area 2 as the first priority, and determine the total capacity coefficient P in the area at this time. y Whether it meets the low temperature stage c The required capacity factor P n ;

[0072] When the conditions are met, the performance data of the refrigeration room unit is output;

[0073] At this time, the total capacity coefficient P in the region y Does not meet the low temperature stage c The required capacity factor P n When setting the second priority: the capacity coefficient P in Area 1Y1 and the capacity coefficient P of Area 2 Y2 Find the total capacity coefficient P in the region within the data range y The largest matching object outputs the performance data of the refrigeration room unit and determines the capacity coefficient P of Area 1 under the output conditions at this time. Y1 and the capacity coefficient P of Area 2 Y2 size;

[0074] When the capacity coefficient P of Area 1 Y1 Greater than the capacity coefficient P of Area 2 Y2 When , it is energy saving mode A;

[0075] When the capacity coefficient P of Area 2 Y2 Greater than the capacity coefficient P of Area 1 Y1 When , it is energy saving mode B;

[0076] The time thresholds of energy-saving mode A and energy-saving mode B are both set to t m , start timing when it is determined that the working modes of Area 1 and Area 2 are both in energy-saving mode and the conditions are not met, and record the energy-saving mode at this time. When the time threshold is reached, determine the working area mode at this time and change the energy-saving mode. The specific process is as follows:

[0077] If in t m At the beginning, it is in energy-saving mode A, that is, the capacity coefficient of Area 1 is P Y1 Greater than the capacity coefficient P of Area 2 Y2 , then at t m At the end, it switches to energy-saving mode B, that is, the capacity coefficient P of Area 2 Y2 Greater than the capacity coefficient P of Area 1 Y1 The loss rate of the refrigeration room unit is calculated by detecting the original efficiency η of the refrigeration room unit and the current efficiency η0 of the refrigeration room unit. The calculation formula is:

[0078]

[0079] The overall loss level of Area 1 is:

[0080]

[0081] The overall loss level of Area2 is:

[0082]

[0083] ω i Expressed as the loss rate of the i-th device;

[0084] Changing the time thresholds of energy-saving mode A and energy-saving mode B according to the overall loss level of the area;

[0085] When ω1>ω2, the time threshold of energy-saving mode A is reduced according to the loss ratio.

[0086]

[0087] When ω1<ω2, the time threshold of the energy-saving mode B state is reduced according to the loss degree ratio.

[0088]

[0089] According to the degree of loss, the time t m Change to t m1 or m2 .

[0090] For example, in the high temperature stage h , the production capacity coefficient P of Area 1 and Area 2 within 6 hours at 38℃ Y1 , P Y2 Both are greater than the capacity coefficient threshold P min At this time, the capacity of each refrigeration room unit is optimized by obtaining the maximum matching object of the capacity coefficient, and the capacity is optimized by changing the operating number and operating output power of the fans, water pumps, and compressors in the refrigeration room unit and outputting the refrigeration room unit data;

[0091] In the low temperature stage c , within 8 hours under -5℃ environment, first determine the capacity coefficient P of Area 1 and Area 2 Y1 , P Y2 Both are within the capacity coefficient threshold P min The total capacity coefficient P in the region under the condition y Whether it meets the low temperature stage c The required capacity factor P n If the conditions are met, the capacity is optimized again and the data of the refrigeration room unit is output. The capacity is optimized and the data of the refrigeration room unit is output by changing the number of fans, water pumps, and compressors in the refrigeration room unit and the operating output power.

[0092] If not satisfied, select energy saving mode:

[0093] The energy-saving mode time period threshold is set to t m=8h, then the time starts from each time the energy-saving mode needs to be selected and stops when the energy-saving mode ends, and each time is 8h; and the time period threshold of the area is changed according to the overall loss degree of the area, and the process is as follows:

[0094] The loss degree of Area 1 is detected, and the result obtained by calculation is ω1 = 89%; the loss degree of Area 2 is detected, and the result obtained by calculation is ω2 = 93%;

[0095] At this time, ω1<ω2, then the time threshold of energy-saving mode B state changes to

[0096] The present invention provides a technical solution: an artificial intelligence-based refrigeration room energy-saving monitoring system, the system comprising: a preprocessing module, a regional control module, a detection module, a data processing module, an analysis module and an execution module;

[0097] The pre-processing module is used to construct a historical database of refrigeration rooms and divide the refrigeration room units in the area into regions based on historical data;

[0098] The regional control module performs zone-merging management on the divided areas, and uniformly sets the values ​​of the refrigeration room units in the area according to the capacity requirements;

[0099] The detection module is used to detect various environmental values ​​in the target terminal space, various input and output values ​​of the refrigeration room unit, and the extreme values ​​and corresponding time points of the day and night temperature changes in the working area;

[0100] The data processing module is used to receive feedback data from the detection module and save various feedback data; the analysis module analyzes the best regional working mode based on the algorithm model and the capacity optimization setting results;

[0101] The execution module is used to receive the optimal regional working mode finally analyzed by the analysis module, and transmit the corresponding data to the regional control module to adjust the refrigeration room unit;

[0102] The output end of the preprocessing module is electrically connected to the input end of the regional control module; the output end of the regional control module is electrically connected to the input end of the data processing module; the output end of the detection module is electrically connected to the input end of the data processing module; the output end of the data processing module is electrically connected to the input end of the analysis module; the output end of the analysis module is electrically connected to the input end of the execution module; the execution module is electrically connected to the regional control module and the data processing module, and the detection module and the analysis module are electrically connected.

[0103] The detection module includes a sensor unit and a stage unit; the sensor unit detects the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit. q , Chilled water temperature T d , ambient temperature T, and set stage data storage; the stage unit monitors t in the working area n The temperature change in the area is recorded, and the temperature change data is obtained to obtain the extreme value of the temperature change in the area and the corresponding time point, and the area is divided into n High temperature stage h and low temperature stage c ; and set and record the energy-saving mode stage time in the energy-saving mode state.

[0104] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0105] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for energy-saving supervision of a refrigeration room based on artificial intelligence, characterized in that: The method comprises the following steps: Step S1, collecting performance data of refrigeration room units, building a refrigeration room history database, analyzing the data in the refrigeration room history database, dividing the refrigeration room units in the working area into two areas, and performing zoning management on the two areas; Step S2, dividing the two time stages by detecting the extreme values ​​of the day and night temperature changes in the working area and the duration at the corresponding temperature; Step S3, constructing an algorithm model, and obtaining the capacity coefficients of the two areas in the time period through various values ​​of the refrigeration room units and the corresponding output power and corresponding energy consumption; The process of building an algorithm model is: Detect the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit q , Chilled water temperature T d , ambient temperature T, and store the data; By combining the linear regression equation: P n =β0+β1T+β2T q +β3T d +e, Among them, β0, β1, β2, β3 represent regression coefficients; ε represents the constant term; it can be obtained that in the high temperature stage h and low temperature stage c The required capacity factor P n ; Step S4, using the capacity coefficient obtained by the algorithm model, selecting the best regional working mode and energy-saving mode in the two time periods according to the capacity coefficient, and adjusting the energy-saving mode according to the loss of the refrigeration room units in the two areas; Best regional working method within the stage: In the high temperature stage h In this case, both Area 1 and Area 2 work in performance mode, and the total capacity coefficient P in the area y Meet the high temperature stage h The required capacity factor P n Under the condition of n Data set, extract the capacity coefficient P in the set y The minimum value is obtained, and the corresponding capacity coefficients of Area 1 and Area 2 and the corresponding fan, water pump, and compressor data are obtained, and finally the performance data of the refrigeration room unit is output; In the low temperature stage c Under this circumstance, the working mode of Area 1 and Area 2 needs to output the performance data of the refrigeration room units after comparing the results of the optimal capacity output. The specific process is as follows: Set the energy-saving mode in Area 1 and Area 2 as the first priority, and determine the total capacity coefficient P in the area at this time. y Whether it meets the low temperature stage c The required capacity factor P n ; When the conditions are met, the performance data of the refrigeration room unit is output; At this time, the total capacity coefficient P in the region y Does not meet the low temperature stage c The required capacity factor P n When setting the second priority: the capacity coefficient P in Area 1 Y1 and the capacity coefficient P of Area 2 Y2 Find the total capacity coefficient P in the region within the data range y The largest matching object outputs the performance data of the refrigeration room unit and determines the capacity coefficient P of Area 1 under the output conditions at this time. Y1 and the capacity coefficient P of Area 2 Y2 size; When the capacity coefficient P of Area 1 Y1 Greater than the capacity coefficient P of Area 2 Y2 When , it is energy saving mode A; When the capacity coefficient P of Area 2 Y2 Greater than the capacity coefficient P of Area 1 Y1 When , it is energy saving mode B; The time period thresholds of energy-saving mode A and energy-saving mode B are both set to t m , start timing when it is determined that the working modes of Area 1 and Area 2 are both in energy-saving mode and the conditions are not met, and record the energy-saving mode at this time. When the time period threshold is reached, determine the working area mode at this time and change the energy-saving mode. The specific process is as follows: If in t m At the beginning, it is in energy-saving mode A, that is, the capacity coefficient of Area 1 is P Y1 Greater than the capacity coefficient P of Area 2 Y2 , then at t m At the end, it switches to energy-saving mode B, that is, the capacity coefficient P of Area 2 Y2 Greater than the capacity coefficient P of Area 1 Y1 .

2. The method for energy-saving supervision of a refrigeration room based on artificial intelligence according to claim 1 is characterized in that: In step S1, the performance data includes the energy consumption data WH of the refrigeration room, the refrigeration data CH, the performance data of the fan, water pump, compressor in the refrigeration room unit, and the cooling water temperature T q , Chilled water temperature T d , ambient temperature T; According to the energy consumption data WH and refrigeration data CH of the refrigeration room unit, the capacity coefficient P of the refrigeration room unit is calculated. The refrigeration room units in the working area are divided into regions according to the obtained capacity coefficients, so that the capacity coefficients of Area 1 and Area 2 are equal, that is: P Y1 =P Y2 , where the number of units in Area 1 is Y1 + the number of units in Area 2 is Y2 = the total number of units in the region is Y, and the regional total capacity coefficient is P y =P Y1 +P Y2 .

3. The method for energy-saving supervision of a refrigeration room based on artificial intelligence according to claim 1 is characterized in that: In step S2, by monitoring t n The temperature changes in the area are recorded, and the temperature change data is obtained to obtain the extreme value T of the temperature change in the area. max , T min and the time t at the corresponding temperature Tmax ,t Tmin , and the corresponding time point T a , T b , T c , T d , divided out at t n High temperature stage h and low temperature stage c .

4. The method for energy-saving supervision of a refrigeration room based on artificial intelligence according to claim 1 is characterized in that: In step S3: the minimum capacity coefficient P of Area 1 and Area 2 is min Set as the capacity coefficient threshold in the region, by comparing the capacity coefficient P in the region with the minimum capacity coefficient P min The relationship between the regional capacity coefficient P> the minimum capacity coefficient P min When the regional working mode is performance mode, when the capacity coefficient P in the region = the minimum capacity coefficient P min At this time, the regional working mode is energy-saving mode.

5. The method for energy-saving supervision of a refrigeration room based on artificial intelligence according to claim 1, characterized in that: In step S4: the loss rate of the refrigeration room unit is calculated by detecting the original efficiency η of the refrigeration room unit and the current efficiency η0 of the refrigeration room unit, and the calculation formula is: The overall loss level of Area 1 is: The overall loss level of Area2 is: Among them, ω i Expressed as the loss rate of the i-th device; Changing the time period thresholds of energy-saving mode A and energy-saving mode B according to the overall loss level of the area; When ω1>ω2, the time threshold of energy-saving mode A is reduced according to the loss ratio. When ω1<ω2, the time threshold of the energy-saving mode B state is reduced according to the loss degree ratio. According to the degree of loss, the time t m Change to t m1 or m2 .

6. A monitoring system for a refrigeration room energy-saving monitoring method based on artificial intelligence applied to any one of claims 1-5, characterized in that: The system includes: a preprocessing module, a regional control module, a detection module, a data processing module, an analysis module and an execution module; The pre-processing module is used to construct a historical database of refrigeration rooms and divide the refrigeration room units in the area into regions based on historical data; The regional control module performs zone-merging management on the divided areas, and uniformly sets the values ​​of the refrigeration room units in the area according to the capacity requirements; The detection module is used to detect various environmental values ​​in the target terminal space, various input and output values ​​of the refrigeration room unit, and the extreme values ​​and corresponding time points of the day and night temperature changes in the working area; The data processing module is used to receive feedback data from the detection module and save various feedback data; the analysis module analyzes the best regional working mode based on the algorithm model and the capacity optimization setting results; The execution module is used to receive the optimal regional working mode finally analyzed by the analysis module, and transmit the corresponding data to the regional control module to adjust the refrigeration room unit; The output end of the preprocessing module is electrically connected to the input end of the regional control module; the output end of the regional control module is electrically connected to the input end of the data processing module; the output end of the detection module is electrically connected to the input end of the data processing module; the output end of the data processing module is electrically connected to the input end of the analysis module; the output end of the analysis module is electrically connected to the input end of the execution module; the execution module is electrically connected to the regional control module and the data processing module, and the detection module and the analysis module are electrically connected.

7. The monitoring system of the refrigeration room energy-saving monitoring method based on artificial intelligence according to claim 6 is characterized by: The analysis module includes an algorithm unit, an optimization unit and a logic unit; The algorithm unit is used to build the algorithm model P n =β0+β1T+β2T q +β3T d +e, Among them, β0, β1, β2, β3 represent regression coefficients; ε represents the constant term; it can be obtained that in the high temperature stage h and low temperature stage c The required capacity factor P n ; The optimization unit is used to monitor the energy consumption data WH and cooling data CH of the refrigeration room units in Area 1 and Area 2 to obtain the capacity coefficient P. The maximum and minimum values ​​of the capacity coefficients of Area 1 and Area 2 form a spatial range to find the total capacity coefficient P in the area. y The largest matching object obtains the fan, pump, and compressor performance data of the capacity object; Logic unit in the low temperature stage c Under the above conditions, the working modes of Area 1 and Area 2 are logically processed, and after obtaining the result of the optimal capacity output, the performance data of the refrigeration room unit are output: when the logic unit performs logical processing, the working modes of Area 1 and Area 2 are both set to the energy-saving mode as the first priority, and the total capacity coefficient P in the area is determined at this time. y Whether it meets the low temperature stage c The required capacity factor P n , when the conditions are met, the performance data of the refrigeration room unit is output; At this time, the total capacity coefficient P in the region y Does not meet the low temperature stage c The required capacity factor P n When setting the second priority: the capacity coefficient P in Area 1 Y1 and the capacity coefficient P of Area 2 Y2 Find the total capacity coefficient P in the region within the space formed y The largest matching object outputs the performance data of the refrigeration room unit and determines the capacity coefficient P of Area 1 under the output conditions at this time. Y1 and the capacity coefficient P of Area 2 Y2 size; When the capacity coefficient P of Area 1 Y1 Greater than the capacity coefficient P of Area 2 Y2 When , it is energy saving mode A; When the capacity coefficient P of Area 1 Y1 Smaller than the capacity coefficient P of Area 2 Y2 When , it is energy saving mode B; The time thresholds of energy-saving mode A and energy-saving mode B are both set to t m , from the logic processing, it is determined that the working modes of Area 1 and Area 2 are both in energy-saving mode and the conditions are not met. The timing starts and the energy-saving mode at this time is recorded. When the time threshold is reached, the working area mode at this time is determined and the energy-saving mode is changed.

8. The monitoring system of the refrigeration room energy-saving monitoring method based on artificial intelligence according to claim 6 is characterized by: The detection module includes a sensor unit and a stage unit; the sensor unit detects the performance data of the fan, water pump, compressor and cooling water temperature T in the refrigeration room unit. q , Chilled water temperature T d , ambient temperature T, and set stage data storage; the stage unit monitors t in the working area n The temperature change in the area is recorded, and the temperature change data is obtained to obtain the extreme value of the temperature change in the area and the corresponding time point, and the area is divided into n High temperature stage h and low temperature stage c ; and set and record the energy-saving mode stage time in the energy-saving mode state.

Images