Centralized cooling early warning system based on Internet of Things

Abstract

The invention discloses a centralized cold supply early warning system based on the Internet of Things, and relates to the technical field of cold supply management.The system comprises a record generation module, an analysis and adjustment module and a key monitoring module, by arranging the analysis and adjustment module, a proportion can be set to analyze a real pre-temperature record in a cold supply building, and the real pre-temperature record in the cold supply building can be monitored; meanwhile, the default proportion of the actual pre-temperature record of the cold supply building extracted in the subsequent period is adjusted in real time according to the actual situation, on the basis that the cold supply situation of the cold supply building is fully monitored, the data analysis amount of different cold supply buildings is reasonably distributed, a key monitoring module is arranged, key monitoring buildings can be marked, and the real-time monitoring effect is achieved. According to the method and the system, the key monitoring buildings can be efficiently and accurately selected from the cold supply buildings corresponding to the centralized cold supply equipment, the early warning rooms can be selected from the key monitoring buildings for early warning, and monitoring and early warning of each cold supply building and each cold supply room are not needed any more.

Description

Technical Field

[0001] This invention relates to the field of cooling management technology, and more specifically, to a centralized cooling early warning system based on the Internet of Things. Background Technology

[0002] With the increasing popularity of centralized heating, centralized cooling is also gradually being used in some areas. Centralized cooling is a cooling method that supplies chilled water to various areas within a building through centralized cooling equipment. Centralized cooling is very suitable for building complexes with high building density and high cooling demand, as it is not only more environmentally friendly but also facilitates centralized management.

[0003] However, centralized cooling systems need to cool rooms in multiple buildings simultaneously, resulting in a large amount of room data and information that needs to be processed at the same time. This leads to an excessive amount of data that the cooling system needs to monitor, putting a heavy burden on the system's analysis. Consequently, when cooling abnormalities occur in some rooms, the centralized cooling system often struggles to issue timely warning signals. Summary of the Invention

[0004] In view of the shortcomings of existing technologies, the purpose of this invention is to provide a centralized cooling early warning system based on the Internet of Things.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A centralized cooling early warning system based on the Internet of Things includes a record generation module, an analysis and adjustment module, and a key monitoring module;

[0007] The record generation module is used to generate actual pre-temperature records for the cooled rooms in the cooled building, specifically:

[0008] Based on a fixed cycle, the actual temperature, set temperature and cooling parameters of the cooling rooms in the cooling building are collected. After each collection, an actual temperature record is generated for each cooling room, and the actual temperature, set temperature and cooling parameters of the actual temperature record are sent to the server for storage via the Internet of Things.

[0009] The analysis and adjustment module is used to adjust the default ratio for extracting pre-temperature records of cooled buildings in subsequent cycles, specifically:

[0010] Extract all pre-temperature records of the same refrigerated building in the current fixed period according to the default ratio, obtain the average temperature deviation of the refrigerated building, set the upper and lower mean deviation values, when the average temperature deviation is greater than or equal to the upper mean deviation, adjust the default ratio for extracting the pre-temperature records of the refrigerated building in subsequent periods upward, and generate the ratio adjustment record in real time; when the lower mean deviation is less than or equal to the average temperature deviation and less than the upper mean deviation, maintain the default ratio for extracting the pre-temperature records of the refrigerated building in subsequent periods; when the average temperature deviation is less than the lower mean deviation, adjust the default ratio for extracting the pre-temperature records of the refrigerated building in subsequent periods downward.

[0011] The key monitoring module is used to mark key monitored buildings and perform early warning analysis on the cooling rooms in the key monitored buildings, specifically:

[0012] Obtain the building re-monitoring value Jz of the cooling building, set the building re-monitoring threshold, and mark the cooling building as a key monitoring building when the building re-monitoring value Jz is greater than or equal to the building re-monitoring threshold. When the building re-monitoring value Jz is less than the building re-monitoring threshold, no corresponding action is taken.

[0013] The system acquires the cooling warning value Eh of the cooling rooms in key monitored buildings, sets a cooling warning threshold, and marks the cooling room as a warning room when the cooling warning value Eh is greater than or equal to the cooling warning threshold. The warning room issues a warning signal, and the analysis and adjustment module prioritizes extracting the actual pre-temperature record of the warning room in the following x fixed periods. When the cooling warning value Eh is less than the cooling warning threshold, no corresponding processing is performed.

[0014] Furthermore, the average temperature deviation of the cooled building is obtained through the following steps: the actual pre-set temperature records extracted according to the default ratio are marked as analysis records; the difference between the actual temperature and the set temperature of the analysis records is calculated and the absolute value is taken to obtain the temperature deviation value; all temperature deviation values ​​are summed and the average value is taken to obtain the average temperature deviation.

[0015] Furthermore, the building re-monitoring value Jz of the cooled building is obtained through the following steps: Obtain all proportional adjustment records for the cooled building within n days prior to the current system time; calculate the difference between the average temperature deviation and the average deviation of the proportional adjustment records to obtain the deviation value; sum all deviation values ​​to obtain the total deviation value, and label it as Dg; obtain the total number of proportional adjustment records, and label it as Sp; sort all proportional adjustment records by their proportional adjustment times in chronological order; calculate the time difference between two adjacent proportional adjustment times after sorting to obtain the proportional adjustment interval; sum all proportional adjustment intervals and take the average to obtain the proportional adjustment average interval, and label it as Cw; then use the formula... Obtain the building re-monitoring value Jz, where a1 is the deviation from the total value coefficient, a2 is the proportional adjustment quantity coefficient, and a3 is the proportional adjustment interval coefficient.

[0016] Furthermore, the cooling warning value Eh for the cooling room in the key monitored building is obtained through the following steps: all actual pre-temperature records of the same cooling room in the key monitored building within m fixed periods before the current system time are marked as key monitoring records. The cooling parameters of the cooling room in the previous fixed period are used as input data for the temperature measurement model. The output data of the temperature measurement model is obtained. The output data of the temperature measurement model is labeled as the predicted temperature. The difference between the actual temperature of the cooling room in the current fixed period and the predicted temperature in the previous fixed period is calculated to obtain the predicted temperature difference. When the predicted temperature difference is ≥0, the predicted temperature difference is marked as the predicted high temperature difference. When the predicted temperature difference is <0, the predicted temperature difference is marked as the predicted low temperature difference. The cooling warning value Eh for the cooling room is obtained.

[0017] Furthermore, the temperature measurement model is obtained through the following steps: acquiring multiple cooling parameters, labeling the cooling parameters as training data, assigning labels to the training data, dividing the training data into training set and validation set according to a set ratio, constructing a neural network model, iteratively training the neural network model using the training set and validation set, determining that the neural network model has completed training when the number of iterations exceeds the iteration threshold, labeling the trained neural network model as the temperature measurement model, which is used to predict the actual temperature of the cooled room in the next fixed cycle, and labeling the output data of the temperature measurement model as the predicted actual temperature of the cooled room in the next fixed cycle, and labeling the predicted actual temperature as the predicted temperature.

[0018] Furthermore, the cooling warning value Eh of the cooling room is obtained through the following steps: summing all predicted high temperature differences and taking the average to obtain the predicted high temperature average difference, which is marked as Tk; obtaining the total number of predicted high temperature differences, which is marked as Cd; summing all predicted low temperature differences and taking the average to obtain the predicted low temperature average difference, which is marked as Sy; obtaining the total number of predicted low temperature differences, which is marked as An; and using the formula Eh=|Tk×a1+Cd×a2-Sy×a3-An×a4|, the cooling warning value Eh of the cooling room is obtained, where a1 is the predicted high temperature average difference coefficient, a2 is the predicted high temperature quantity coefficient, a3 is the predicted low temperature average difference coefficient, and a4 is the predicted low temperature quantity coefficient.

[0019] Furthermore, the actual temperature record includes the actual temperature, the set temperature, and the cooling parameters.

[0020] Furthermore, the percentage adjustment record includes the percentage adjustment time and the average temperature deviation.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] 1. The analysis and adjustment module can be set to analyze the actual pre-temperature records of the cooled buildings at a set ratio. At the same time, the default ratio of the actual pre-temperature records of the cooled buildings can be adjusted in real time according to the actual situation. While ensuring sufficient monitoring of the cooling situation of the cooled buildings, the data analysis volume of different cooled buildings can be reasonably allocated to avoid excessive system analysis pressure.

[0023] 2. The key monitoring module can mark key monitoring buildings and perform early warning analysis on the cooling rooms in key monitoring buildings. It can efficiently and accurately select key monitoring buildings from the cooling buildings corresponding to the centralized cooling equipment, and select early warning rooms from the key monitoring buildings for early warning, eliminating the need to monitor and issue early warnings for every cooling building and cooling room. Attached Figure Description

[0024] Figure 1 This is a block diagram illustrating the principle of the analysis and adjustment module of the present invention.

[0025] Figure 2 This is a schematic diagram of the key monitoring module of the present invention. Detailed Implementation

[0026] Example 1

[0027] Reference Figure 1 A centralized cooling early warning system based on the Internet of Things includes a record generation module and an analysis and adjustment module.

[0028] The record generation module is used to generate actual pre-temperature records for cooled rooms in refrigerated buildings, specifically:

[0029] Based on a fixed cycle, the actual temperature, set temperature, and cooling parameters of the cooled rooms in the refrigerated building are collected. Each time data is collected, a pre-temperature record is generated for each refrigerated room, and the actual temperature, set temperature, and cooling parameters in the pre-temperature record are transmitted to a server for storage via the Internet of Things (IoT). For example, if the fixed cycle is 1 hour, then every hour, the actual temperature (i.e., the indoor temperature of the refrigerated room measured by a thermometer or other temperature measuring device), the set temperature (i.e., the set temperature of the centralized cooling equipment), and cooling parameters (including but not limited to the valve opening degree of the cooling pipes, coolant flow rate, and the actual power of the exhaust fan) of the refrigerated rooms in the refrigerated building are collected. The pre-temperature record includes the actual temperature, set temperature, and cooling parameters.

[0030] The analysis and adjustment module is used to adjust the default ratio for extracting pre-temperature records of cooled buildings in subsequent cycles, specifically:

[0031] The default ratio is used to extract all actual pre-temperature records of the same cooling building in the current fixed period. For example, if the default ratio is 30%, then in each period, 30% of the actual pre-temperature records of the same cooling building (each actual pre-temperature record corresponds to one cooling room) will be extracted (that is, the actual pre-temperature records of 30% of the rooms in the cooling building will be extracted).

[0032] The average temperature deviation of the cooled building is obtained through the following steps: The actual pre-temperature records extracted at the default ratio are marked as analysis records. The difference between the actual temperature and the set temperature in the analysis records is calculated, and the absolute value is taken to obtain the temperature deviation value. All temperature deviation values ​​are summed and averaged to obtain the average temperature deviation. Upper and lower mean deviations are set. When the average temperature deviation is greater than or equal to the upper mean deviation, the default ratio for extracting the actual pre-temperature records of the cooled building in subsequent periods is adjusted upwards, and a ratio adjustment record is generated in real time, including the ratio adjustment time (i.e., the time when the ratio adjustment record is generated) and the average temperature deviation. When the lower mean deviation is less than or equal to the average temperature deviation and less than the upper mean deviation, the default ratio for extracting the actual pre-temperature records of the cooled building in subsequent periods is maintained. When the average temperature deviation is less than the lower mean deviation, the default ratio for extracting the actual pre-temperature records of the cooled building in subsequent periods is adjusted downwards. The default percentage for extracting pre-cooled temperature records from refrigerated buildings in subsequent cycles can be adjusted upwards or downwards, and the adjustment range can be adjusted according to system settings. The analysis and adjustment module allows setting a percentage for analyzing pre-cooled temperature records from refrigerated buildings and adjusting the default percentage for subsequent cycles in real time based on actual conditions. This ensures sufficient monitoring of the cooling situation in refrigerated buildings while rationally allocating the data analysis workload for different buildings, avoiding excessive system analysis pressure.

[0033] Example 2

[0034] Reference Figure 2 Based on Example 1, it also includes a key monitoring module, which is used to mark key monitored buildings and perform early warning analysis on the cooling rooms in the key monitored buildings, specifically:

[0035] To obtain the building re-monitoring value Jz for a cooled building, the following steps are taken: Obtain all proportional adjustment records for the cooled building within n days prior to the current system time. Calculate the difference between the average temperature deviation and the average deviation of each proportional adjustment record to obtain the deviation value. Sum all deviation values ​​to obtain the total deviation value, labeled as Dg. Obtain the total number of proportional adjustment records, labeled as Sp. Sort all proportional adjustment records by their proportional adjustment times in chronological order. Calculate the time difference between two adjacent proportional adjustment times after sorting to obtain the proportional adjustment interval. Sum all proportional adjustment intervals and take the average to obtain the average proportional adjustment interval, labeled as Cw. Then, use the formula... Obtain the building re-monitoring value Jz, where a1 is the deviation coefficient from the total value, a2 is the proportional adjustment quantity coefficient, and a3 is the proportional adjustment interval coefficient. The values ​​of a1, a2, and a3 are 0.48, 0.35, and 0.89, respectively. Set a building re-monitoring threshold. When the building re-monitoring value Jz is greater than or equal to the building re-monitoring threshold, the cooling building is marked as a key monitoring building. When the building re-monitoring value Jz is less than the building re-monitoring threshold, no corresponding action is taken.

[0036] To obtain the cooling warning value Eh for the cooling rooms in key monitored buildings, the following steps are taken: Mark all actual predicted temperature records of the same cooling room in the key monitored building within m fixed periods prior to the current system time as key monitoring records. Use the cooling parameters of the key monitoring records for that cooling room in the previous fixed period as input data for the temperature measurement model. Obtain the output data of the temperature measurement model and label the output data as the predicted temperature (predicted temperature for the current fixed period). The temperature measurement model is obtained through the following steps: Obtain multiple cooling parameters... The system uses a numerical method to predict the actual temperature of a room in a given fixed period. The actual temperature is recorded in the current fixed period and the predicted temperature in the previous fixed period is calculated to obtain the predicted temperature difference. When the predicted temperature difference is ≥0, it is marked as the predicted high temperature difference; when the predicted temperature difference is <0, it is marked as the predicted low temperature difference. This process yields the cooling warning value Eh for the room. The system then uses the training and validation sets to construct a neural network model. The model is iteratively trained using the training and validation sets. When the number of iterations exceeds a threshold, the neural network model is considered complete. The trained neural network model is then designated as a temperature prediction model. The temperature prediction model is used to predict the actual temperature of the room in the next fixed period. The output data of the temperature prediction model is labeled with the predicted actual temperature of the room in the next fixed period, and the predicted actual temperature is marked as the predicted temperature difference. The cooling warning value Eh for the cooled room is obtained through the following steps: Sum all predicted high temperature differences and take the average to obtain the average predicted high temperature difference, denoted as Tk. Obtain the total number of predicted high temperature differences, denoted as Cd. Sum all predicted low temperature differences and take the average to obtain the average predicted low temperature difference, denoted as Sy. Obtain the total number of predicted low temperature differences, denoted as An. The cooling warning value Eh for the cooled room is obtained using the formula Eh=|Tk×a1+Cd×a2-Sy×a3-An×a4|, where a1 is the predicted high temperature difference coefficient, a2 is the predicted high temperature quantity coefficient, a3 is the predicted low temperature difference coefficient, and a4 is the predicted low temperature quantity coefficient. The values ​​of a1 are 0.75, a2 are 0.53, a3 are 0.74, and a4 are 0.54. Set a cooling warning threshold. When the cooling warning value Eh is greater than or equal to the cooling warning threshold, the room to be cooled is marked as a warning room. The warning room issues a warning signal. The analysis and adjustment module will prioritize extracting the actual pre-temperature record of the warning room in the following x fixed cycles (if the default proportion of extracting actual pre-temperature records of the cooling building to which the warning room belongs in each cycle is 30%, then in the following x fixed cycles, the actual pre-temperature record of the warning room will be extracted from this 30% proportion in each cycle). When the cooling warning value Eh is less than the cooling warning threshold, no corresponding action is taken.The key monitoring module can mark key monitoring buildings and perform early warning analysis on the cooling rooms in key monitoring buildings. It can efficiently and accurately select key monitoring buildings from the cooling buildings corresponding to the centralized cooling equipment, and select early warning rooms from the key monitoring buildings for early warning, eliminating the need to monitor and issue early warnings for every cooling building and cooling room.

[0037] Working principle:

[0038] The analysis and adjustment module allows users to set a ratio for analyzing pre-cooled temperature records in refrigerated buildings. It also adjusts the default ratio for extracting pre-cooled temperature records in subsequent cycles based on actual conditions. This ensures adequate monitoring of cooling conditions while rationally allocating data analysis workload across different refrigerated buildings, preventing excessive system load. The key monitoring module allows users to mark key monitoring buildings and perform early warning analysis on refrigerated rooms within those buildings. This efficiently and accurately selects key monitoring buildings from those with centralized cooling systems and identifies rooms within them for early warning, eliminating the need for monitoring and issuing warnings for every single refrigerated building and room.

[0039] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of this template.

[0040] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A centralized cooling system with early warning based on the Internet of Things, characterized in that, It includes a record generation module, an analysis and adjustment module, and a key monitoring module; The record generation module is used to generate actual pre-temperature records for the cooled rooms in the cooled building, specifically: Based on a fixed cycle, the actual temperature, set temperature and cooling parameters of the cooling rooms in the cooling building are collected. After each collection, an actual temperature record is generated for each cooling room, and the actual temperature, set temperature and cooling parameters of the actual temperature record are sent to the server for storage via the Internet of Things. The analysis and adjustment module is used to adjust the default ratio for extracting pre-temperature records of cooled buildings in subsequent cycles, specifically: Extract all pre-temperature records of the same refrigerated building in the current fixed period according to the default ratio, obtain the average temperature deviation of the refrigerated building, set the upper and lower mean deviation values, when the average temperature deviation is greater than or equal to the upper mean deviation, adjust the default ratio for extracting the pre-temperature records of the refrigerated building in subsequent periods upward, and generate the ratio adjustment record in real time; when the lower mean deviation is less than or equal to the average temperature deviation and less than the upper mean deviation, maintain the default ratio for extracting the pre-temperature records of the refrigerated building in subsequent periods; when the average temperature deviation is less than the lower mean deviation, adjust the default ratio for extracting the pre-temperature records of the refrigerated building in subsequent periods downward. The key monitoring module is used to mark key monitored buildings and perform early warning analysis on the cooling rooms in the key monitored buildings, specifically: Obtain the building re-monitoring value Jz of the cooling building, set the building re-monitoring threshold, and mark the cooling building as a key monitoring building when the building re-monitoring value Jz is greater than or equal to the building re-monitoring threshold. When the building re-monitoring value Jz is less than the building re-monitoring threshold, no corresponding action is taken. The system acquires the cooling warning value Eh of the cooling rooms in key monitored buildings, sets a cooling warning threshold, and marks the cooling room as a warning room when the cooling warning value Eh is greater than or equal to the cooling warning threshold. The warning room issues a warning signal, and the analysis and adjustment module prioritizes extracting the actual pre-temperature record of the warning room in the following x fixed periods. When the cooling warning value Eh is less than the cooling warning threshold, no corresponding processing is performed.

2. The centralized cooling early warning system based on the Internet of Things according to claim 1, characterized in that, The average temperature deviation of the cooled building is obtained through the following steps: the actual pre-set temperature records extracted according to the default ratio are marked as analysis records; the difference between the actual temperature and the set temperature of the analysis records is calculated and the absolute value is taken to obtain the temperature deviation value; all temperature deviation values ​​are summed and the average value is taken to obtain the average temperature deviation.

3. The centralized cooling early warning system based on the Internet of Things according to claim 2, characterized in that, The building re-monitoring value Jz of the cooled building is obtained through the following steps: Obtain all proportional adjustment records for the cooled building within n days prior to the current system time; calculate the difference between the average temperature deviation and the average deviation of the proportional adjustment records to obtain the deviation value; sum all deviation values ​​to obtain the total deviation value, and label it as Dg; obtain the total number of proportional adjustment records, and label it as Sp; sort all proportional adjustment records by their proportional adjustment time in chronological order; calculate the time difference between two adjacent proportional adjustment times after sorting to obtain the proportional adjustment interval; sum all proportional adjustment intervals and take the average to obtain the proportional adjustment average interval, and label it as Cw; then use the formula... Obtain the building re-monitoring value Jz, where a1 is the deviation from the total value coefficient, a2 is the proportional adjustment quantity coefficient, and a3 is the proportional adjustment interval coefficient.

4. A centralized cooling system based on the Internet of Things (IoT) for early warning, as described in claim 3, is characterized in that... The cooling warning value Eh for the cooling room in the key monitored building is obtained through the following steps: all actual pre-temperature records of the same cooling room in the key monitored building within m fixed periods before the current system time are marked as key monitoring records. The cooling parameters of the cooling room in the previous fixed period are used as input data for the temperature measurement model. The output data of the temperature measurement model is obtained. The output data of the temperature measurement model is labeled as the predicted temperature. The difference between the actual temperature of the cooling room in the current fixed period and the predicted temperature in the previous fixed period is calculated to obtain the predicted temperature difference. When the predicted temperature difference is ≥0, the predicted temperature difference is marked as the predicted high temperature difference. When the predicted temperature difference is <0, the predicted temperature difference is marked as the predicted low temperature difference. The cooling warning value Eh for the cooling room is obtained.

5. A centralized cooling system based on the Internet of Things (IoT) for early warning, as described in claim 4, is characterized in that... The temperature measurement model is obtained through the following steps: acquiring multiple cooling parameters, labeling the cooling parameters as training data, assigning labels to the training data, dividing the training data into training and validation sets according to a set ratio, constructing a neural network model, iteratively training the neural network model using the training and validation sets, determining that the neural network model has completed training when the number of iterations exceeds the iteration threshold, and labeling the trained neural network model as the temperature measurement model. The temperature measurement model is used to predict the actual temperature of the cooled room in the next fixed cycle. The label of the output data of the temperature measurement model is the predicted actual temperature of the cooled room in the next fixed cycle, and the predicted actual temperature is labeled as the predicted temperature.

6. A centralized cooling system based on the Internet of Things (IoT) for early warning, as described in claim 5, is characterized in that... The cooling warning value Eh for the cooled room is obtained through the following steps: sum up all predicted high temperature differences and take the average to obtain the average predicted high temperature difference, which is marked as Tk; obtain the total number of predicted high temperature differences and mark it as Cd; sum up all predicted low temperature differences and take the average to obtain the average predicted low temperature difference, which is marked as Sy; obtain the total number of predicted low temperature differences and mark it as An; use the formula Eh=|Tk×a1+Cd×a2-Sy×a3-An×a4| to obtain the cooling warning value Eh for the cooled room, where a1 is the predicted high temperature difference coefficient, a2 is the predicted high temperature quantity coefficient, a3 is the predicted low temperature difference coefficient, and a4 is the predicted low temperature quantity coefficient.

7. A centralized cooling system based on the Internet of Things (IoT) for early warning, as described in claim 6, is characterized in that... The actual pre-temperature record includes the actual temperature, the set temperature, and the cooling parameters.

8. A centralized cooling system based on the Internet of Things (IoT) for early warning, as described in claim 7, is characterized in that... The percentage adjustment record includes the percentage adjustment time and the average temperature deviation.

Images