An energy-saving optimization control method for refrigeration station system based on artificial intelligence
Through artificial intelligence-based methods, personalized and dynamic energy-saving optimization is carried out for the refrigeration station system, which solves the problem that static regulation in the existing technology cannot adapt to seasons and weather changes, and achieves efficient energy-saving optimization of the refrigeration station system.
Patent Information
- Application Number
- CN202411248660.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-06
AI Technical Summary
The prior art lacks personalization and dynamicity in energy saving optimization of refrigeration station systems, and the static equipment parameter regulation cannot adapt to seasonal and weather changes, resulting in poor refrigeration performance.
Using an artificial intelligence-based method, by retrieving basic information of the refrigeration station, creating experimental data, combining equipment parameters, simulated operation and feedback optimal parameters, ensure that the simulation process focuses on representative demand scenarios, considers the impact of seasons and weather, and conducts comprehensive scoring. Analysis is performed to determine the optimal parameter combination.
It improves the accuracy and reliability of simulation results, ensures the authenticity of refrigeration demand and energy-saving optimization, provides scientific operation guidance, and promotes energy-saving optimization of refrigeration station systems.
Smart Images

Figure CN118761141B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of refrigeration system control, and in particular to an energy-saving optimization control method for a refrigeration station system based on artificial intelligence. Background Art
[0002] The demand for refrigeration in supermarkets, data centers, etc. is constantly increasing. Therefore, the development of energy-saving and optimized control methods for refrigeration station systems is of great significance for improving refrigeration efficiency and reducing energy consumption.
[0003] In the prior art, there are also some related solutions involving energy-saving optimization of refrigeration station systems. For example, the invention patent application for energy-saving optimization control system of high-efficiency cold station refrigeration system with patent publication number CN217110112U has a data acquisition control box placed on the top of the control platform in terms of hardware, with a built-in transverse movement mechanism for maintenance. A wire take-up groove is provided on the back of the control box, and a data acquisition interface is configured on the top to effectively manage cable connections. The wire take-up assembly is embedded in the groove to enhance cleanliness and protection. The transverse movement mechanism is fixed to the mobile base plate by side baffles and sliding brackets to prevent dust and facilitate cable arrangement. It has a compact structure, high cost-effectiveness, enhanced practicality and ease of maintenance, and solves the defects of the simple and rigid external structure of the existing refrigeration station system.
[0004] Another patent application with the patent publication number CN112050379A is for an invention patent application of a regional air-conditioning system energy-saving optimization operation control system, which includes a server group, a regional cooling station energy-saving control subsystem, a building energy-saving control subsystem, and an air-conditioning terminal equipment energy-saving control subsystem. It provides the overall framework and design ideas of the regional cooling energy-saving control system, solves the quality and quantity regulation problems of the regional cooling system, establishes a control model for the average indoor temperature of the air-conditioned rooms in the building, and uses PID control methods to solve the control problems of large time lag and parameter uncertainty characteristics of the regional cooling system.
[0005] Although the above scheme proposes some solutions for energy-saving optimization of refrigeration station systems, the existing technology still has limitations. Specifically, the existing technology often adopts a general optimization strategy for energy-saving optimization of existing projects in refrigeration station systems, that is, static equipment parameter control. On the one hand, it does not take into account the actual situation and environmental conditions of specific projects, ignores the individuality and differentiation of projects, and may fail to fully utilize the potential energy-saving space of the refrigeration station system. On the other hand, the refrigeration demand will change with the changes in seasons, weather and other factors. Static equipment parameter control may not be able to adapt to this dynamic change, resulting in poor refrigeration performance of the refrigeration station system in certain periods. Summary of the invention
[0006] In order to overcome the shortcomings of the background technology, an embodiment of the present invention provides an energy-saving optimization control method for a refrigeration station system based on artificial intelligence, which can effectively solve the problems involved in the above-mentioned background technology.
[0007] The purpose of the present invention can be achieved through the following technical solutions: an artificial intelligence-based refrigeration station system energy-saving optimization control method, including: S1. Project basic information retrieval: Retrieve the basic information of the target project of the refrigeration station, including the fixed configuration parameters of each refrigeration equipment in the refrigeration station in the current season, the energy consumption information of each historical working day of the refrigeration station in the current season, the building location of the corresponding refrigeration building area and its refrigeration information of each historical working day of the current season.
[0008] S2. Creation of refrigeration experiment data: based on the refrigeration information of the target project corresponding to the refrigeration building area in the current season on each historical working day, create each group of refrigeration experiment data of the target project corresponding to the refrigeration building area in the current season.
[0009] S3. Creation of equipment experimental parameter combinations: According to the adjustable value ranges of each refrigeration equipment in the refrigeration station corresponding to the target project stored in the WEB cloud, the fixed configuration parameters of each refrigeration equipment in the refrigeration station of the target project in the current season are randomly adjusted and configured to create various experimental parameter combinations of the refrigeration equipment of the target project in the current season.
[0010] S4. Conventional refrigeration operation simulation: configure the experimental parameter combinations of the target project's refrigeration equipment in the current season respectively, simulate the conventional refrigeration operation of the corresponding refrigeration building area under each group of refrigeration experimental data, and evaluate the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the corresponding refrigeration building area of the target project in the current season based on the energy consumption information of each working day in the history of the refrigeration station.
[0011] S5. Simulation result report feedback: Generate a report based on the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the refrigeration building area of the target project in the current season, and provide feedback.
[0012] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention determines the conventional refrigeration space volume and conventional refrigeration period of the refrigeration building area corresponding to the target project, limits the subsequent conventional refrigeration operation simulation premise from both spatial and temporal perspectives, ensures that the simulation process focuses on the most representative refrigeration demand scenario, reduces the interference of irrelevant variables, and thus improves the accuracy and reliability of the simulation results.
[0013] (2) The present invention analyzes the average cooling demand load of each unit cooling time in the conventional cooling period for the conventional cooling space volume in the corresponding cooling building area of the target project under various weather conditions in the current season, fully considers the dynamic impact of seasons and weather conditions on the cooling demand load of the cooling building area, ensures the authenticity and reliability of subsequent conventional cooling operation simulation data, and effectively promotes energy-saving optimization of the refrigeration station system.
[0014] (3) The present invention conducts a comprehensive simulation scoring analysis from four perspectives: economic benefit, energy consumption optimization, equipment health, and refrigeration effectiveness, so as to scientifically and accurately confirm the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the refrigeration building area of the target project in the current season, thereby providing effective guidance and support for the operation and management of the refrigeration system of the target project. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.
[0016] Figure 1 The present invention is a flowchart of the steps for implementing the method. DETAILED DESCRIPTION
[0017] 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.
[0018] Reference Figure 1 As shown, the present invention provides an energy-saving optimization control method for a refrigeration station system based on artificial intelligence, including: S1. Project basic information retrieval: retrieving the basic information of the target project of the refrigeration station, including the fixed configuration parameters of each refrigeration equipment in the refrigeration station in the current season, the energy consumption information of each historical working day of the refrigeration station in the current season, the building location of the corresponding refrigeration building area and the refrigeration information of each historical working day of the current season.
[0019] It should be noted that the above-mentioned target project refers to a refrigeration station system that has been completed and put into operation, which is an existing project.
[0020] It should also be noted that the basic information of the above-mentioned target project is retrieved from the refrigeration station project management platform.
[0021] Specifically, the target project corresponds to the cooling information of the cooling building area on each historical working day of the season, including the cooling space volume , cooling period, cooling demand load of each unit cooling time within the cooling period , The numbers of the historical working days in the quarter. , is the historical working days of the season, It is the number of cooling time of each unit in the cooling period. , It is the number of unit cooling hours in the cooling period.
[0022] The energy consumption information of each historical working day of the refrigeration station in the current season includes the refrigeration energy consumption of each unit refrigeration time in the refrigeration period.
[0023] S2. Creation of refrigeration experiment data: based on the refrigeration information of the target project corresponding to the refrigeration building area in the current season on each historical working day, create each group of refrigeration experiment data of the target project corresponding to the refrigeration building area in the current season.
[0024] Specifically, the creation of each group of refrigeration experimental data of the target project corresponding to the refrigeration building area in the current season includes: extracting the refrigeration space volume and refrigeration period from the refrigeration information of each historical working day in the current season of the target project corresponding to the refrigeration building area, summarizing the historical working days, cumulative refrigeration space volume and cumulative refrigeration time of the target project corresponding to the refrigeration building area in the current season, and taking the ratio of the cumulative refrigeration space volume, the cumulative refrigeration time and the historical working days as the conventional refrigeration space volume of the target project corresponding to the refrigeration building area in the current season. , normal cooling time.
[0025] Calculate the cooling demand load for each unit cooling time in the cooling period for each historical working day of the season for the cooling building area of the target project for the conventional cooling space volume .
[0026] Filter out the common cooling periods in the cooling periods of each historical working day in the current season in the cooling building area corresponding to the target project, and compare the corresponding cooling time with the conventional cooling time. If the comparison relationship is greater than or equal to, the common cooling period is used as the conventional cooling period in the current season in the cooling building area corresponding to the target project; if the comparison relationship is less than, the common cooling period is evenly extended until the duration reaches the conventional cooling time, and the extended common cooling period is used as the conventional cooling period.
[0027] It should be noted that the balanced extension process of the common cooling period is as follows: the absolute deviation between the cooling time corresponding to the common cooling period and the normal cooling time is obtained, and the The product of the absolute deviation duration is used as the reference duration. The reference duration is extended forward from the start time point of the common cooling period and extended backward from the end time point to obtain the normal cooling period.
[0028] The meteorological parameters of each historical working day of the season for the building location of the target project corresponding to the refrigeration building area are extracted from the Meteorological Bureau, including the temperature, humidity and light intensity values of each unit cooling time during the regular cooling period, and the weather condition types of each historical working day of the season for the refrigeration building area corresponding to the target project are analyzed.
[0029] It should be noted that the temperature value, humidity value and light intensity value of each unit cooling time in the above-mentioned conventional cooling period are respectively the average temperature value, average humidity value and average light intensity value in the corresponding time.
[0030] The embodiment of the present invention determines the conventional refrigeration space volume and conventional refrigeration period of the refrigeration building area corresponding to the target project, limits the subsequent conventional refrigeration operation simulation premise from both spatial and temporal perspectives, ensures that the simulation process focuses on the most representative refrigeration demand scenario, reduces the interference of irrelevant variables, and thus improves the accuracy and reliability of the simulation results.
[0031] The weather conditions of each working day in the current season are sorted out. The average cooling demand load for each unit cooling time in the conventional cooling period for the conventional cooling space volume in each weather condition type in the corresponding cooling building area of the target project is extracted and calculated, and a cooling demand load sequence for the conventional cooling period is generated in chronological order, and then the cooling demand load sequence for the conventional cooling period for the conventional cooling space volume in each weather condition type in the corresponding cooling building area of the target project is obtained, which is used as each group of cooling experimental data for the corresponding cooling building area of the target project in the season, wherein the number of the weather condition type corresponds to the number of the cooling experimental data group one by one.
[0032] It should be noted that the various groups of refrigeration experimental data for the refrigeration building area corresponding to the above-mentioned target project in the current season specifically refer to the average refrigeration demand load for each unit refrigeration time of the conventional refrigeration space in the refrigeration building area corresponding to the target project during the conventional refrigeration period on working days corresponding to each weather condition type. The average refrigeration demand load refers to the average calculation of the refrigeration demand load for each unit refrigeration time of the conventional refrigeration space volume during the conventional refrigeration period on working days with the same weather condition type.
[0033] Specifically, the The calculation formula is: .
[0034] Specifically, the analysis target project corresponds to the weather condition type of each historical working day in the current season in the refrigeration building area, including: according to the temperature value interval, humidity value interval and light intensity value interval corresponding to each weather condition type stored in the WEB cloud, obtain the reference temperature value and its reasonable deviation temperature value, reference humidity value and its reasonable deviation humidity value, reference light intensity value and its reasonable light intensity deviation value corresponding to each weather condition type, respectively recorded as , , ,in is the number of each weather condition type, , is the number of weather condition types, combined with the temperature value of each unit cooling time during the regular cooling period of each working day in the current season at the location of the building in the cooling building area corresponding to the target project , humidity value and light intensity values ,in It is the number of cooling time of each unit in the regular cooling period. , The number of unit cooling hours during the regular cooling period is used to calculate the similarity between the weather conditions of each historical working day in the season and each weather condition type in the cooling building area corresponding to the target project. , , select the weather condition type with the maximum similarity as the weather condition type of each historical working day in the current season in the cooling building area corresponding to the target project.
[0035] It should be noted that the method for obtaining the reference temperature values and reasonable deviation temperature values corresponding to the above-mentioned weather condition types is: the reference temperature value corresponding to each weather condition type is obtained by averaging the upper and lower limits of the temperature numerical range corresponding to each weather condition type, and the absolute difference between the reference temperature value corresponding to each weather condition type and the upper limit value of its corresponding temperature numerical range is used as the reasonable deviation temperature value corresponding to each weather condition type. Similarly, the reference humidity value and its reasonable deviation humidity value, reference light intensity value and its reasonable light intensity deviation value corresponding to each weather condition type are obtained.
[0036] The embodiment of the present invention analyzes the average refrigeration demand load of each unit refrigeration time in the conventional refrigeration period for the conventional refrigeration space volume in the corresponding refrigeration building area of the target project under various weather conditions in the current season, fully considers the dynamic impact of seasons and weather conditions on the refrigeration demand load of the refrigeration building area, ensures the authenticity and reliability of subsequent conventional refrigeration operation simulation data, and effectively promotes energy-saving optimization of the refrigeration station system.
[0037] S3. Creation of equipment experimental parameter combinations: According to the adjustable value ranges of each refrigeration equipment in the refrigeration station corresponding to the target project stored in the WEB cloud, the fixed configuration parameters of each refrigeration equipment in the refrigeration station of the target project in the current season are randomly adjusted and configured to create various experimental parameter combinations of the refrigeration equipment of the target project in the current season.
[0038] S4. Conventional refrigeration operation simulation: configure the experimental parameter combinations of the target project's refrigeration equipment in the current season respectively, simulate the conventional refrigeration operation of the corresponding refrigeration building area under each group of refrigeration experimental data, and evaluate the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the corresponding refrigeration building area of the target project in the current season based on the energy consumption information of each working day in the history of the refrigeration station.
[0039] It should be noted that the above-mentioned configuration target project's experimental parameter combinations of the refrigeration equipment in the current season and the simulation of the conventional refrigeration operation of the corresponding refrigeration building area under each set of refrigeration experimental data are realized through the refrigeration station system simulation platform.
[0040] Specifically, the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the refrigeration building area corresponding to the target project in the current season includes: obtaining the conventional refrigeration operation simulation results of each experimental parameter combination of the refrigeration equipment of the target project in the current season for each group of refrigeration experimental data, including the energy consumption optimization coefficient , Economic Benefit Coefficient , Equipment Health Factor and refrigeration efficiency coefficient ,in is the number of each experimental parameter combination, , is the number of experimental parameter combinations, is the number of each group of refrigeration experimental data, , is the number of groups of refrigeration experimental data, calculated by the model The comprehensive simulation score of the conventional refrigeration operation simulation of each group of refrigeration experimental data for each experimental parameter combination of the refrigeration equipment in the refrigeration building area of the target project in the current season is obtained, where They are the weight proportions corresponding to the preset energy consumption optimization coefficient, economic benefit coefficient, equipment health coefficient and refrigeration effectiveness coefficient.
[0041] With each group of refrigeration experimental data as the horizontal axis and each experimental parameter combination of the refrigeration equipment as the vertical axis, the comprehensive simulation score is filled in the corresponding position to construct a conventional refrigeration operation simulation score table for the target project in the current season, and the experimental parameter combination of the refrigeration equipment corresponding to the maximum comprehensive simulation score in the column where each group of refrigeration experimental data is located is selected as the corresponding optimal refrigeration equipment experimental parameter combination.
[0042] The embodiment of the present invention conducts a comprehensive simulation scoring analysis from four perspectives: economic benefit, energy consumption optimization, equipment health, and refrigeration effectiveness, so as to scientifically and accurately confirm the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the refrigeration building area of the target project in the current season, thereby providing effective guidance and support for the operation and management of the refrigeration system of the target project.
[0043] Specifically, the The acquisition process includes: monitoring the experimental parameter combinations of the target project's refrigeration equipment in the current season, and simulating the refrigeration energy consumption of each unit of refrigeration time during the conventional refrigeration operation of each group of refrigeration experimental data. .
[0044] It should be noted that the above The data is obtained through the energy consumption monitoring tool in the refrigeration station system simulation platform.
[0045] According to the energy consumption information of each working day in the current season of the refrigeration station, the historical refrigeration energy consumption of each unit of refrigeration time in the normal refrigeration period during the normal refrigeration operation of the target project with fixed configuration parameter combinations for each group of refrigeration experimental data is calculated. .
[0046] It should be noted that the above-mentioned fixed configuration parameter combination of the target project in the current season refers to the fixed configuration parameters of each refrigeration equipment in the refrigeration station in the current season in the basic information of the target project. The calculation process is as follows: extract the cooling energy consumption of each unit cooling time during the cooling period of each working day in the current season, and The calculation method is consistent with that of the refrigeration station. The refrigeration energy consumption of each unit refrigeration time in the refrigeration period under the conventional refrigeration space volume for each historical working day of the season is obtained. According to the conventional refrigeration period, the refrigeration energy consumption of each unit refrigeration time in the conventional refrigeration space volume for each historical working day of the season is further extracted. According to the weather condition type of each historical working day of the season, the average refrigeration energy consumption of each unit refrigeration time in the conventional refrigeration period under the conventional refrigeration space volume of the refrigeration station in the current season under each weather condition type is sorted and calculated. This is used as the historical refrigeration energy consumption of each unit refrigeration time in the conventional refrigeration period during the conventional refrigeration operation of each group of refrigeration experimental data for the fixed configuration parameter combination of the target project in the season. The number of each weather condition type corresponds to the number of the refrigeration experiment data group.
[0047] By formula The refrigeration experimental data of each group of target projects in the current season are obtained, and the refrigeration energy consumption is cumulatively optimized during the conventional refrigeration period during the conventional refrigeration operation simulation process for each group of refrigeration experimental data.
[0048] By calculating the formula get ,in is a natural constant.
[0049] Specifically, the The acquisition process includes: extracting the electricity unit price of the cooling station stored in the WEB cloud, and Multiply the accumulated electricity price saved in the conventional refrigeration operation simulation process of each group of refrigeration experimental data of the target project in the current season, and use the ratio of it to the preset reference electricity price as .
[0050] Specifically, the The acquisition process includes: real-time collection of each group of refrigeration experimental data of the target project in the current season; comparison of the monitoring values of each key operating indicator of each refrigeration equipment in the refrigeration station during the conventional refrigeration operation simulation of each group of refrigeration experimental data with the reasonable value range of each key operating indicator of each refrigeration equipment in the refrigeration station stored in the WEB cloud; evaluation of the operating risk index of each refrigeration equipment in the refrigeration station during the conventional refrigeration operation simulation of each group of refrigeration experimental data of the target project in the current season; ,in It is the number of each refrigeration equipment in the refrigeration station. , is the number of refrigeration equipment in the refrigeration station, calculated by the formula get .
[0051] It should be noted that the evaluation process of the operation risk index of each refrigeration equipment in the above-mentioned refrigeration station is: obtain the deviation value of the monitoring value of each key operation indicator corresponding to each refrigeration equipment in the refrigeration station and its reasonable numerical range, as the risk value of each key operation indicator corresponding to each refrigeration equipment in the refrigeration station, and use the ratio of it to the monitoring value of each key operation indicator corresponding to each refrigeration equipment in the refrigeration station as the operation risk factor of each key operation indicator corresponding to each refrigeration equipment in the refrigeration station, and accumulate them to obtain the operation risk index of each refrigeration equipment in the refrigeration station, where if the monitoring value of each key operation indicator corresponding to each refrigeration equipment in the refrigeration station is within its reasonable numerical range, its risk value is recorded as 0.
[0052] Exemplarily, the key operating indicator monitoring values corresponding to each refrigeration equipment in the above-mentioned refrigeration station specifically refer to: the refrigeration compressor and its key operating indicators: compression ratio, cooling capacity, energy efficiency ratio, suction pressure, exhaust pressure, and motor current.
[0053] Condenser and its key operating indicators: condensing temperature, cooling water temperature difference, cooling water flow rate, heat exchange efficiency.
[0054] Throttling device and its key operating indicators: superheat, evaporating pressure, flow control accuracy.
[0055] Evaporator and its key operating indicators: evaporating temperature, evaporating pressure, cooling capacity, and heat exchange efficiency.
[0056] Specifically, the The acquisition process includes: real-time monitoring of each group of refrigeration experimental data of the target project in the current season; the refrigeration speed of each unit refrigeration time in the conventional refrigeration period during the conventional refrigeration operation simulation of each group of refrigeration experimental data; the ratio of the refrigeration speed to the preset reference refrigeration speed is used as the refrigeration efficiency factor of each unit refrigeration time in the conventional refrigeration period; and further calculation is performed through the mean to obtain .
[0057] S5. Simulation result report feedback: Generate a report based on the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the refrigeration building area of the target project in the current season, and provide feedback.
[0058] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.
Claims
1. An energy-saving optimization control method for a refrigeration station system based on artificial intelligence, characterized in that: include: S1. Basic project information retrieval: retrieve the basic information of the target refrigeration station project, including the fixed configuration parameters of each refrigeration equipment in the refrigeration station in the current season, the energy consumption information of each working day in the history of the refrigeration station in the current season, the building location of the corresponding refrigeration building area and the refrigeration information of each working day in the history of the current season; S2. Creation of refrigeration test data: based on the refrigeration information of the target project corresponding to the refrigeration building area in the current season on each historical working day, create each set of refrigeration test data of the target project corresponding to the refrigeration building area in the current season; S3. Creation of equipment experimental parameter combinations: According to the adjustable value range of each refrigeration equipment in the refrigeration station corresponding to the target project stored in the WEB cloud, the fixed configuration parameters of each refrigeration equipment in the refrigeration station of the target project in the current season are randomly adjusted and configured to create various experimental parameter combinations of the refrigeration equipment of the target project in the current season; S4. Conventional refrigeration operation simulation: configure the experimental parameter combinations of the target project's refrigeration equipment in the current season, simulate the conventional refrigeration operation of the corresponding refrigeration building area under each group of refrigeration experimental data, and evaluate the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the corresponding refrigeration building area of the target project in the current season in combination with the energy consumption information of each working day in the history of the refrigeration station; S5. Simulation result report feedback: Generate a report based on the optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the current season in the target project corresponding to the refrigeration building area, and provide feedback; The target project corresponds to the cooling information of the cooling building area for each historical working day of the season, including the cooling space volume , cooling period, cooling demand load of each unit cooling time within the cooling period , The numbers of the historical working days in the quarter. , is the historical working days of the season, It is the number of cooling time of each unit in the cooling period. , It is the number of unit cooling hours in the cooling period; The energy consumption information of each historical working day of the refrigeration station in the current season includes the refrigeration energy consumption of each unit refrigeration time in the refrigeration period; The creating of each group of refrigeration experimental data of the refrigeration building area corresponding to the target project in the current season includes: extracting the refrigeration space volume and refrigeration time period from the refrigeration information of each historical working day of the refrigeration building area corresponding to the target project in the current season, summarizing the historical working days, cumulative refrigeration space volume and cumulative refrigeration time of the refrigeration building area corresponding to the target project in the current season, and taking the ratio of the cumulative refrigeration space volume, the cumulative refrigeration time and the historical working days as the conventional refrigeration space volume of the refrigeration building area corresponding to the target project in the current season. , conventional cooling time; Calculate the cooling demand load for each unit cooling time in the cooling period for each historical working day of the season for the cooling building area of the target project for the conventional cooling space volume ; Filter out the common cooling periods in the cooling periods of each historical working day in the current season in the cooling building area corresponding to the target project, and compare the corresponding cooling duration with the conventional cooling duration. If the comparison relationship is greater than or equal to, the common cooling period is used as the conventional cooling period in the current season in the cooling building area corresponding to the target project. If the comparison relationship is less than, the common cooling period is evenly extended until the duration reaches the conventional cooling duration, and the extended common cooling period is used as the conventional cooling period; Extract the meteorological parameters of each historical working day of the season for the building location of the target project's corresponding cooling building area from the Meteorological Bureau, including the temperature value, humidity value and light intensity value of each unit cooling time during the regular cooling period, and analyze the weather condition type of each historical working day of the season for the target project's corresponding cooling building area; The weather conditions of each working day in the current season are sorted out. Extract and calculate the average cooling demand load of each unit cooling time in the conventional cooling period for the conventional cooling space volume in the corresponding cooling building area of the target project under each weather condition type in the current season, generate a cooling demand load sequence of the conventional cooling period in chronological order, and then obtain the cooling demand load sequence of the conventional cooling period for the conventional cooling space volume in the corresponding cooling building area of the target project under each weather condition type in the current season, and use this as each group of cooling experimental data of the corresponding cooling building area of the target project in the current season, wherein the number of the weather condition type corresponds to the number of the cooling experimental data group one by one; Said The calculation formula is: ; The optimal refrigeration equipment experimental parameter combination corresponding to each group of refrigeration experimental data in the current season of the refrigeration building area corresponding to the evaluation target project includes: obtaining the conventional refrigeration operation simulation results of each experimental parameter combination of the refrigeration equipment of the target project in the current season for each group of refrigeration experimental data, including the energy consumption optimization coefficient , Economic Benefit Coefficient , Equipment Health Factor and refrigeration efficiency coefficient ,in is the number of each experimental parameter combination, , is the number of experimental parameter combinations, is the number of each group of refrigeration experimental data, , is the number of groups of refrigeration experimental data, calculated by the model The comprehensive simulation score of the conventional refrigeration operation simulation of each group of refrigeration experimental data for each experimental parameter combination of the refrigeration equipment in the refrigeration building area of the target project in the current season is obtained, where They are the weight proportions corresponding to the preset energy consumption optimization coefficient, economic benefit coefficient, equipment health coefficient and refrigeration effectiveness coefficient; With each group of refrigeration experimental data as the horizontal axis and each experimental parameter combination of refrigeration equipment as the vertical axis, the comprehensive simulation score is filled in the corresponding position to construct a conventional refrigeration operation simulation score table for the refrigeration building area corresponding to the target project in the current season, and the experimental parameter combination of refrigeration equipment corresponding to the maximum comprehensive simulation score in the column where each group of refrigeration experimental data is located is selected as the corresponding optimal refrigeration equipment experimental parameter combination.
2. The method for energy-saving optimization control of a refrigeration station system based on artificial intelligence according to claim 1, characterized in that: The analysis target project corresponds to the weather condition type of each historical working day in the current season in the refrigeration building area, including: according to the temperature value interval, humidity value interval and light intensity value interval corresponding to each weather condition type stored in the WEB cloud, the reference temperature value and its reasonable deviation temperature value, the reference humidity value and its reasonable deviation humidity value, the reference light intensity value and its reasonable light intensity deviation value corresponding to each weather condition type are obtained, which are recorded as , , ,in is the number of each weather condition type, , is the number of weather condition types, combined with the temperature value of each unit cooling time during the regular cooling period of each working day in the current season at the location of the building in the cooling building area corresponding to the target project , humidity value and light intensity values ,in It is the number of cooling time of each unit in the regular cooling period. , The number of unit cooling hours during the regular cooling period is used to calculate the similarity between the weather conditions of each historical working day in the season and each weather condition type in the cooling building area corresponding to the target project. , , select the weather condition type with the maximum similarity as the weather condition type of each historical working day in the current season in the cooling building area corresponding to the target project.
3. The method for energy-saving optimization control of a refrigeration station system based on artificial intelligence according to claim 1, characterized in that: Said The acquisition process includes: monitoring the experimental parameter combinations of the target project's refrigeration equipment in the current season, and simulating the refrigeration energy consumption of each unit of refrigeration time during the conventional refrigeration operation of each group of refrigeration experimental data. ; According to the energy consumption information of each working day in the current season of the refrigeration station, the historical refrigeration energy consumption of each unit of refrigeration time in the regular refrigeration period during the regular refrigeration operation of the target project corresponding to the refrigeration building area with fixed configuration parameters for each group of refrigeration experimental data is calculated. ; By formula Obtain the refrigeration experimental data of each group of target projects in the current season, and optimize the refrigeration energy consumption cumulatively during the conventional refrigeration period during the conventional refrigeration operation simulation process of each group of refrigeration experimental data; By calculating the formula get ,in is a natural constant.
4. The method for energy-saving optimization control of a refrigeration station system based on artificial intelligence according to claim 3 is characterized in that: Said The acquisition process includes: extracting the electricity unit price of the cooling station stored in the WEB cloud, and Multiply the accumulated electricity price saved in the conventional refrigeration operation simulation process of each group of refrigeration experimental data of the target project in the current season, and use the ratio of it to the preset reference electricity price as .
5. The method for energy-saving optimization control of a refrigeration station system based on artificial intelligence according to claim 1, characterized in that: Said The acquisition process includes: real-time collection of each group of refrigeration experimental data of the target project in the current season; comparison of the monitoring values of each key operating indicator of each refrigeration equipment in the refrigeration station during the conventional refrigeration operation simulation of each group of refrigeration experimental data with the reasonable value range of each key operating indicator of each refrigeration equipment in the refrigeration station stored in the WEB cloud; evaluation of the operating risk index of each refrigeration equipment in the refrigeration station during the conventional refrigeration operation simulation of each group of refrigeration experimental data of the target project in the current season; ,in It is the number of each refrigeration equipment in the refrigeration station. , is the number of refrigeration equipment in the refrigeration station, calculated by the formula get .
6. The method for energy-saving optimization control of a refrigeration station system based on artificial intelligence according to claim 1, characterized in that: Said The acquisition process includes: real-time monitoring of each group of refrigeration experimental data of the target project in the current season; the refrigeration speed of each unit refrigeration time in the conventional refrigeration period during the conventional refrigeration operation simulation of each group of refrigeration experimental data; the ratio of the refrigeration speed to the preset reference refrigeration speed is used as the refrigeration efficiency factor of each unit refrigeration time in the conventional refrigeration period; and further calculation is performed through the mean to obtain .
