A high-efficiency refrigeration room performance optimization method and device

Abstract

This invention discloses a high-efficiency refrigeration room performance optimization method and device, which relates to the field of intelligent energy-saving optimization technology. The method includes collecting and preprocessing refrigeration equipment operating data using multiple sensors; constructing an MT-LSTM model based on the preprocessed operating data to predict future cooling load demand and generate a cooling load demand forecast; generating an optimized scheduling strategy based on the cooling load demand forecast using the NSGA-II optimization algorithm; and, based on the optimized scheduling strategy, executing device startup and shutdown and load ratio distribution through the Internet of Things (IoT), monitoring operating data in real time, and dynamically adjusting and optimizing the operating status of the refrigeration equipment. By constructing an MT-LSTM model to predict future cooling load demand, the present invention achieves accurate demand forecasting.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent energy-saving optimization, and in particular to a method and device for optimizing the performance of a high-efficiency refrigeration machine room. Background Art

[0002] In recent years, with the rapid adoption of intelligent management and energy-saving technologies, refrigeration rooms, as a crucial component of building heating and cooling systems, have garnered widespread attention. Existing technologies primarily rely on traditional refrigeration control strategies, using simple sensors to sense variables such as ambient temperature and humidity, followed by manual adjustments based on empirical rules. With the introduction of the Internet of Things and artificial intelligence (AI), advanced intelligent control systems are increasingly being applied to refrigeration rooms, enhancing both intelligence and automation. Furthermore, LSTM and multi-objective optimization algorithms have demonstrated significant potential in prediction and optimization, providing a viable path for more efficient refrigeration equipment scheduling.

[0003] Although traditional refrigeration management systems have met cooling load demands to a certain extent, they still have many shortcomings in the real-time and accuracy of data collection and processing, as well as the intelligent level of scheduling optimization. Traditional systems often rely on manual control, resulting in significant energy consumption, high failure rates, and difficulty in meeting dynamically changing cooling load demands. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a high-efficiency refrigeration room performance optimization method to solve the energy consumption management problem.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for optimizing the performance of an efficient refrigeration room, comprising collecting operating data of refrigeration equipment through a variety of sensors and performing preprocessing; constructing an MT-LSTM model based on the preprocessed operating data to predict future cooling load demand and generate a cooling load demand prediction value; generating an optimized scheduling strategy based on the cooling load demand prediction value through the NSGA-II optimization algorithm; according to the optimized scheduling strategy, executing device startup and shutdown and load ratio distribution through the IoT, and monitoring the operating data in real time to dynamically adjust and optimize the operating status of the refrigeration equipment.

[0008] As a preferred solution of the high-efficiency refrigeration room performance optimization method of the present invention, the operation data of the equipment includes ambient temperature data, ambient humidity data, equipment status data and historical load data.

[0009] As a preferred solution of the high-efficiency refrigeration room performance optimization method of the present invention, the preprocessing includes denoising, data standardization and missing value filling.

[0010] As a preferred solution of the high-efficiency refrigeration room performance optimization method of the present invention, wherein: based on the pre-processed operating data, the MT-LSTM model is constructed to predict the future cooling load demand and generate the cooling load demand prediction value, the specific steps are:

[0011] Perform weighted fusion on the pre-processed running data to generate a unified data set;

[0012] Divide the unified dataset into training set, validation set and test set;

[0013] Build an MT-LSTM model based on LSTM, define the MT-LSTM model input as the training set, and the output as the cooling load demand forecast value;

[0014] Extract the time series data from the training set, split it into multiple time periods according to the time steps of the time series data, form a time segment sequence, and input it into the multi-layer LSTM for processing;

[0015] The first LSTM layer receives the time segment sequence, processes the time segment sequence through the gating mechanism, captures the short-term dependency information, and inputs it to the second LSTM layer;

[0016] The second LSTM layer receives short-term dependency information, processes it through gating mechanisms and filtering, captures medium-term dependency information, and inputs it to the third LSTM layer;

[0017] The third LSTM layer receives medium-term dependency information, combines the short-term dependency information of the first LSTM layer and the medium-term dependency information of the second LSTM layer through a gating mechanism, captures long-term dependency information, and outputs it to the fully connected layer;

[0018] The fully connected layer receives and integrates short-term dependency information, medium-term dependency information, and long-term dependency information to calculate the cooling load demand forecast value, which is expressed as:

[0019]

[0020] in, is the predicted value of cooling load demand, D is the cooling load demand, pred is the predicted value, T e,t is the ambient temperature data at time point t, H e,t is the ambient humidity data at the tth time point, e is the environmental identifier, S t is the equipment operating status data at the tth time point, D t-1 is the historical load data at the t-th time point, t is the time, and m is the total time;

[0021] Use the validation set to evaluate the performance of the MT-LSTM model and adjust the parameters;

[0022] The test set is used to measure the generalization ability and prediction accuracy of the MT-LSTM model.

[0023] As a preferred solution of the high-efficiency refrigeration room performance optimization method of the present invention, wherein: based on the cooling load demand forecast value, the optimization scheduling strategy is generated by the NSGA-II optimization algorithm, and the specific steps are:

[0024] Select the NSGA-II optimization algorithm and define the optimization objective as minimizing the energy consumption of the refrigeration equipment;

[0025] Set the start-up and shutdown times of multiple refrigeration devices according to the cooling load forecast value, and distribute the load proportions of multiple refrigeration devices;

[0026] Convert the start-up time, shutdown time and load ratio distribution of each refrigeration equipment into chromosome code;

[0027] Generate an initial scheduling plan based on chromosome encoding using the NSGA-II optimization algorithm;

[0028] Optimize the initial scheduling plan through cross simulation and mutation simulation to generate a new scheduling plan;

[0029] According to the new scheduling scheme, the total energy consumption of the refrigeration equipment is calculated as follows:

[0030]

[0031] Among them, E is the total energy consumption of refrigeration equipment, P i (t) is the power of the i-th device at time t, Q i (t) is the operating time of the i-th device, i is the device, and n is the total number of devices;

[0032] The total energy consumption of the refrigeration equipment in the new scheduling scheme is evaluated by the non-dominated sorting method to generate the optimal scheduling strategy.

[0033] As a preferred solution of the high-efficiency refrigeration room performance optimization method of the present invention, wherein: the NSGA-II optimization algorithm is used to generate an initial scheduling plan based on chromosome coding, and the specific steps are:

[0034] Define the start time of chromosome encoding as a five-bit binary number to generate the initial chromosome;

[0035] Define the closing time of chromosome encoding as a five-bit binary number to generate the initial chromosome;

[0036] Define the load ratio of chromosome encoding as a four-bit binary number to generate the initial chromosome;

[0037] The initial chromosomes of startup time, shutdown time and load ratio distribution are combined to generate encoding information;

[0038] The coded information is disassembled and decoded to obtain the specific start-up time, shutdown time and load ratio distribution of each refrigeration equipment, and generate an initial scheduling plan.

[0039] As a preferred solution of the high-efficiency refrigeration room performance optimization method of the present invention, wherein: according to the optimization scheduling strategy, the device startup and shutdown and load ratio distribution are executed through IoT, and the operation data is monitored in real time to dynamically adjust and optimize the operation status of the refrigeration equipment. The specific steps are:

[0040] Extracting the start-up time, shut-down time and load ratio distribution of refrigeration equipment from the optimization scheduling strategy as control instructions;

[0041] Establish connections between each refrigeration equipment and the Internet of Things through IoT;

[0042] The control instructions for extracting the start-up time, shutdown time and load ratio distribution of the refrigeration equipment are sent to the corresponding refrigeration equipment through IoT to start, shut down and distribute the load ratio;

[0043] Use ambient temperature sensors, ambient humidity sensors, and equipment operating status monitors to collect operating data in real time;

[0044] The collected real-time operation data is transmitted and stored in the central control center via IoT;

[0045] The central control center uses the support vector machine algorithm to monitor the operating data in real time. When the operating data is abnormal, it indicates that the equipment has failed.

[0046] The central control center automatically sends alarms and initiates adjustments based on equipment failures;

[0047] If there is a slight abnormality, the load ratio distribution and temperature parameters of the refrigeration equipment will be automatically adjusted;

[0048] If there is a serious abnormality, start the backup refrigeration equipment.

[0049] In a second aspect, the present invention provides a high-efficiency refrigeration room performance optimization device, including an acquisition module, a prediction module, an optimization module and a monitoring module; the acquisition module is used to collect operating data of refrigeration equipment through multiple sensors and perform preprocessing; the prediction module is used to construct an MT-LSTM model based on the preprocessed operating data to predict future cooling load demand and generate a cooling load demand prediction value; the optimization module is used to generate an optimized scheduling strategy based on the cooling load demand prediction value through the NSGA-II optimization algorithm; the monitoring module is used to execute equipment startup and shutdown and load ratio distribution through IoT according to the optimized scheduling strategy, and monitor the operating data in real time, dynamically adjust and optimize the operating status of the refrigeration equipment.

[0050] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the high-efficiency refrigeration room performance optimization method as described in the first aspect of the present invention is implemented.

[0051] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the high-efficiency refrigeration room performance optimization method as described in the first aspect of the present invention is implemented.

[0052] The beneficial effects of the present invention are as follows: the present invention predicts future cooling load demand by constructing an MT-LSTM model, thereby achieving accurate demand forecasting, which plays an important role in optimizing the scheduling of refrigeration equipment. The MT-LSTM model can capture short-term, medium-term and long-term dependency information, and generate reliable cooling load demand forecast values ​​by processing a variety of feature data. In this way, even in the face of complex environmental changes and equipment operating conditions, the MT-LSTM model can still provide accurate demand forecasts, thereby avoiding over-cooling or under-cooling, improving the overall efficiency of refrigeration equipment operation, reducing unnecessary energy consumption, and ensuring the accurate satisfaction of cooling load demand. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0055] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0056] Example 1: This example provides a method for optimizing the performance of a high-efficiency refrigeration room, comprising the following steps:

[0057] S1. Collect the operating data of the refrigeration equipment through various sensors and perform preprocessing.

[0058] Furthermore, multiple sensors are deployed to monitor multiple key parameters of the refrigeration room in real time;

[0059] Collect ambient temperature data through ambient temperature sensors;

[0060] Collect ambient humidity data through an ambient humidity sensor;

[0061] Collect environmental humidity data through humidity sensors;

[0062] The equipment operation status monitor collects equipment status data. The equipment operation status monitor includes current / voltage sensors, vibration sensors, temperature sensors and pressure sensors;

[0063] Current / voltage sensors are used to measure the current and voltage data of equipment during operation to infer the load status of the equipment. By monitoring the current and voltage data in real time, the workload and efficiency of the equipment can be evaluated.

[0064] Vibration sensors are used to monitor the vibration data of equipment (such as compressors, pumps, etc.) to determine whether there is abnormal vibration and thus determine the health status of the equipment;

[0065] Temperature sensors are used to monitor temperature changes in equipment such as compressors and cooling towers, obtain temperature data, and determine their operating conditions;

[0066] Pressure sensors are used to measure pressure changes in equipment and obtain pressure data, such as the pressure in the cooling cycle, which can help determine the working status of the refrigeration;

[0067] Through these equipment operation status monitors, data such as equipment operation status, load conditions, and health status can be collected in real time to provide a reference for changes in cooling load;

[0068] Collect historical load data from historical operations, including cooling demand data over a certain period of time in the past;

[0069] Use signal filters to remove noise data from multiple sensor acquisition processes;

[0070] To ensure the homogeneity of the input run data, normalization was used to convert all run data into the same dimensional range;

[0071] Fill missing values ​​in the running data through interpolation or other methods to ensure the integrity of the running data;

[0072] It should be noted that by deploying a variety of sensors for real-time monitoring, comprehensively collecting the ambient temperature, ambient humidity and equipment status data of the refrigeration room, and combining it with historical load data, a comprehensive data foundation can be provided; signal filters are used to remove noise to ensure the quality of operating data; standardization processing and missing value filling ensure the consistency and integrity of the input operating data; effectively improve the accuracy and completeness of the operating data, provide reliable data support for subsequent cold load prediction and scheduling optimization, and greatly improve the accuracy and efficiency of monitoring and optimized scheduling.

[0073] S2. Based on the preprocessed operating data, an MT-LSTM model is constructed to predict future cooling load demand and generate a cooling load demand forecast value.

[0074] Furthermore, the pre-processed running data is weighted and fused to generate a unified data set; the expression is:

[0075] X′ t =α×T e,t +β×H e,t +γ×S t +δ×D t-1 ;

[0076] Among them, X' t is the unified data set after preprocessing, α is the weight coefficient of the ambient temperature data, T e,t The ambient temperature data at the tth time point, β is the weight coefficient of the ambient temperature data, H e,t is the ambient humidity data at the tth time point, e is the environment, S t is the equipment operation status data at the tth time point, γ is the weight coefficient of the equipment operation status data, D t-1 is the historical load at the t-th time point, δ is the weight coefficient of the historical load data, and t is the time;

[0077] Divide the unified dataset into training, validation, and test sets. A common ratio is 70% for training, 15% for validation, and 15% for testing.

[0078] Build an MT-LSTM model based on LSTM, define the MT-LSTM model input as the training set, and the output as the cooling load demand forecast value;

[0079] Extract the time series data from the training set and split it into multiple time periods based on the time step of the time series data (such as hourly, daily, etc.) to form a time segment sequence. Input it to the multi-layer LSTM for processing. For example, the data of the past n time steps is used as an input time segment. The number of input time segments is determined by the length of the unified data set and the time step size.

[0080] The first layer of LSTM receives the time segment sequence, processes it through the gating mechanism (input gate, forget gate, output gate), captures short-term dependency information, and inputs it to the second layer of LSTM;

[0081] Specifically, the first layer of LSTM receives the time segment sequence of input ambient temperature data, humidity data, equipment status data, and historical load data;

[0082] The input gate of the gating mechanism determines how much new input information to accept. It combines the new data of the current time step (a time slice consisting of ambient temperature, humidity, device status, and historical load data) with the short-term information generated in the previous time step to evaluate which new inputs should be memorized. The decision on how much new input information to accept is based on this data (a time slice consisting of ambient temperature, humidity, device status, and historical load data).

[0083] The forget gate of the gating mechanism processes the comprehensive analysis between short-term dependency information and historical information in the unified dataset to decide how much historical information to retain and discard;

[0084] The output gate of the gating mechanism combines the input data (ambient temperature data, ambient humidity data, device status data, and historical load data) and the memory unit state data (i.e., the memory information accumulated from past time steps) to generate the hidden state output, capture the short-term dependency information, and generate the short-term dependency information after updating and pass it to the second layer LSTM;

[0085] The second LSTM layer receives short-term dependency information, processes it through gating mechanisms and filtering, captures medium-term dependency information, and inputs it to the third LSTM layer;

[0086] Specifically, the short-term dependency information received by the second layer LSTM is the hidden state and memory unit state data passed from the first layer LSTM;

[0087] The input data processed by the input gate of the gating mechanism includes both short-term dependency information from the first layer and new time-segment data in the unified dataset. This is used to evaluate the new input information received and capture medium-term information by combining the output of the first layer with new time-segment data (such as ambient temperature data, ambient humidity data, equipment status data, and historical load data).

[0088] The forget gate of the gating mechanism combines the time segment data in the unified dataset and the output of the first layer of LSTM to process and decide how much short-term information to retain and discard to update the memory unit state;

[0089] The output gate of the gating mechanism integrates the input, memory cell state and short-term information to generate a new hidden state output, capture medium-term dependency information, and pass it to the third layer LSTM as output;

[0090] The third LSTM layer receives medium-term dependency information, combines the short-term dependency information of the first LSTM layer and the medium-term dependency information of the second LSTM layer through a gating mechanism, captures long-term dependency information, and outputs it to the fully connected layer;

[0091] Specifically, the third-layer LSTM receives the medium-term dependency information of the second layer as a new input time segment sequence (such as ambient temperature data, ambient humidity data, equipment status data, and historical load data);

[0092] The new input data processed by the input gate of the gating mechanism includes the medium-term dependency information from the second layer and the time segment data in the unified dataset, which comprehensively analyzes and captures long-term information;

[0093] The forget gate of the gating mechanism combines the output information of the first two layers (short-term dependency information and medium-term dependency information) with the latest input time segment sequence (ambient temperature, humidity, device status, and historical load data). It comprehensively processes the time information and decides how much information to retain and discard to update the memory unit state.

[0094] The output gate of the gating mechanism integrates input, memory, and medium-term information to generate a new hidden state output, capture long-term dependency information, and pass it to the fully connected layer as output;

[0095] The fully connected layer receives and integrates short-term dependency information, medium-term dependency information, and long-term dependency information to calculate the cooling load demand forecast value, which is expressed as:

[0096]

[0097] in, is the cooling load demand forecast value, which represents the cooling load demand forecast value at the future time point t, D is the cooling load demand, which is the variable to be predicted, pred is the predicted value, T e,t is the ambient temperature data at time point t, H e,t is the ambient humidity data at the t-th time point, e is the environmental identifier, which is used to distinguish and identify that a specific variable is related to the environment, S t is the equipment operating status data at the tth time point, D t-1 is the historical load data at the t-th time point, t is the time, and m is the total time;

[0098] Use the validation set to evaluate the performance of the MT-LSTM model and adjust the parameters to improve the generalization ability of the MT-LSTM model;

[0099] Specifically, during the MT-LSTM model training process, the validation set data is often used to evaluate the MT-LSTM model at regular intervals (such as each epoch);

[0100] The validation set data is input into the MT-LSTM model to generate the cooling load demand forecast value;

[0101] Calculate the loss value (such as mean square error, root mean square error, etc.) between the predicted value of cooling load demand and the actual value of the validation set;

[0102] Calculate accuracy (such as accuracy, recall, F1 score, etc. in classification tasks);

[0103] Adjust the hyperparameters of the MT-LSTM model (such as learning rate, batch size, etc.) based on the loss value and accuracy evaluation results of the validation set;

[0104] If the loss on the validation set does not continue to decrease, or if overfitting occurs (low training loss but high validation loss), you may need to adjust the MT-LSTM model structure (such as increasing or decreasing the number of LSTM layers or changing the number of neurons).

[0105] Set an early stopping strategy to terminate training early when the validation set loss value no longer decreases to prevent the MT-LSTM model from overfitting;

[0106] The test set is used to measure the generalization ability and prediction accuracy of the MT-LSTM model. Specifically, after completing the MT-LSTM model training and verification, the best-performing MT-LSTM model is used for the final test set evaluation.

[0107] The test set data is input into the MT-LSTM model to generate the cooling load demand forecast value;

[0108] Calculate the loss value (such as mean square error) between the predicted value of cooling load demand and the actual value of the test set;

[0109] Calculate accuracy (such as accuracy, recall, F1 score, etc. in classification tasks);

[0110] Compare the loss values ​​and accuracy on the training set, validation set, and test set to evaluate the generalization ability and prediction accuracy of the MT-LSTM model on unseen data;

[0111] Use the evaluation results on the test set as a reference indicator for the final MT-LSTM model performance to ensure effectiveness in real-world data applications;

[0112] It should be noted that by constructing an MT-LSTM model and accurately predicting future cooling load demand, the scheduling strategy of refrigeration equipment can be effectively optimized; by capturing short-term, medium-term and long-term dependency information through a multi-layer MT-LSTM model, a cooling load demand forecast value is generated based on a comprehensive analysis of ambient temperature, humidity, equipment status and historical load data; reasonable weighted fusion and time series processing further improve the prediction accuracy; ultimately, an accurate cooling load demand forecast value is provided, which significantly reduces energy consumption, fully meets dynamic cooling load demand, and improves the operational efficiency and reliability of the entire refrigeration system.

[0113] S3. Based on the predicted value of cooling load demand, the optimized scheduling strategy is generated through the NSGA-II optimization algorithm.

[0114] Furthermore, the NSGA-II optimization algorithm was selected to handle the multi-objective optimization problem. The optimization objective was defined as minimizing the energy consumption of the cooling equipment (while meeting the cooling load demand value and other cooling goals, the total energy consumption of the cooling equipment was reduced as much as possible by optimizing the scheduling strategy), while ensuring that the cooling load demand forecast value was met.

[0115] Set the start-up and shutdown times of multiple refrigeration devices according to the cooling load forecast value, and distribute the load proportions of multiple refrigeration devices;

[0116] Specifically, it collects cooling load demand forecasts and equipment status data, and analyzes load changes at different time points;

[0117] Arrange equipment to start up in advance according to peak load periods to ensure adequate cooling before peak loads;

[0118] According to the load reduction trend, arrange for equipment to be gradually shut down and reasonably adjust the equipment operating load;

[0119] Divide the predicted cooling load demand into several time periods to ensure that the load ratio is appropriately distributed in each time period;

[0120] Calculate the load requirements of each device in different time periods to ensure that the total load meets the cooling load forecast value and that each device operates within a reasonable load range;

[0121] Convert the start-up time, shutdown time and load ratio distribution of each refrigeration equipment into chromosome code;

[0122] Specifically, it is agreed that each gene bit of the chromosome represents device and time information, such as bits 1-5 represent the startup time of device 1, and bits 6-10 represent the load ratio distribution of device 1;

[0123] According to the set coding rules, the equipment startup, shutdown and load ratio distribution are converted into independent chromosomes to prepare for the subsequent optimization algorithm input;

[0124] For example, suppose there are three refrigeration devices, and the on / off status and load ratio distribution of the i-th device in a specific time period need to be encoded as follows;

[0125] The coding details are that the start time and the shut down time are represented by 5-bit binary numbers (for example, the maximum value is 23, which is 5 bits, that is, 00000 to 10111 represents 24-hour points);

[0126] The load ratio distribution is represented by a 4-bit binary number (0000 to 1111, corresponding to 0.0 to 1.0);

[0127] The time points of device startup and shutdown within 24 hours are represented by 0-23;

[0128] The equipment load ratio is expressed on a scale of 0-1, so 0.5 represents 50% equipment load;

[0129] Assume there are three devices (A, B, C), and encode their on / off times and load ratio distribution;

[0130] The startup time of device A is: 2 (2 am), and the conversion code is: 00010;

[0131] The closing time is: 10 (10 am), and the conversion code is: 01010;

[0132] The load ratio is: 0.6, and the conversion code is: 1001;

[0133] The startup time of device B is: 6 (6 am), and the conversion code is: 00110;

[0134] The closing time is: 18 (6pm), and the conversion code is: 10010;

[0135] The load ratio is: 0.8, and the conversion code is: 1100;

[0136] The startup time of device C is: 8 (8 am), and the conversion code is: 01000;

[0137] The closing time is: 16 (4 p.m.), and the conversion code is: 10000;

[0138] The load ratio is: 0.4, and the conversion code is: 0110;

[0139] The device codes of devices A, B and C are combined into chromosome codes as follows: 000100101010011000100101100000010000100000110;

[0141] Generate an initial scheduling plan based on chromosome encoding using the NSGA-II optimization algorithm;

[0142] Furthermore, the start time of chromosome encoding is defined as a five-bit binary number to generate the initial chromosome;

[0143] Define the closing time of chromosome encoding as a five-bit binary number to generate the initial chromosome;

[0144] Define the load ratio of chromosome encoding as a four-bit binary number to generate the initial chromosome;

[0145] The initial chromosomes of startup time, shutdown time and load ratio distribution are combined to generate encoding information;

[0146] The coded information is disassembled and decoded to obtain the specific start-up time, shutdown time and load ratio distribution of each refrigeration equipment, and generate an initial scheduling plan.

[0147] For example:

[0148] Set the cooling to three, namely A, B and C;

[0149] Among them, device A: start time 2 (00010), shutdown time 10 (01010), load ratio 0.6 (1001);

[0150] Device B: start time 6 (00110), shut down time 18 (10010), load ratio 0.8 (1100);

[0151] Device C: start time 8 (01000), shut down time 16 (10000), load ratio 0.4 (0110);

[0152] Then the initial chromosomes of A, B and C are combined to generate the encoding information: 000100101010011000100101100000010000100000110;

[0153] Based on the combined coded information, it is then disassembled and decoded to obtain the specific start-up time, shutdown time and load ratio distribution of each refrigeration equipment;

[0154] Time 0-1: All devices are turned off;

[0155] Time 2-6: Device A starts, load 0.6;

[0156] Time 6-8: Devices A and B start up, load A: 0.6, B: 0.8;

[0157] Time 8-10: Devices A, B, and C start up, load A: 0.6, B: 0.8, C: 0.4;

[0158] Time 10-16: Devices B and C start up, and the load is distributed according to the load ratio;

[0159] Time 16-18: Device B is running and C is stopped;

[0160] Time 18-24: All equipment is turned off;

[0161] By iteratively repeating the above encoding and decoding, the specific start-up time, shutdown time, and load ratio distribution of each refrigeration equipment are obtained, and multiple initial scheduling plans are generated to ensure the diversity of the population (e.g., 20-100 initial scheduling plans);

[0162] Optimize the initial scheduling plan through cross simulation and mutation simulation to generate a new scheduling plan;

[0163] Specifically, the chromosomes with better genes are selected from the initial scheduling scheme through crossover simulation, and a new scheduling scheme is generated through crossover operations (such as pairwise crossover recombination);

[0164] Through mutation simulation, some chromosomes are randomly selected and new scheduling schemes are generated through mutation operations (such as randomly changing gene bit information) to ensure diversity;

[0165] Repeatedly conduct crossover and mutation simulations to evaluate new scheduling solutions and continuously optimize scheduling strategies;

[0166] According to the new scheduling scheme, the total energy consumption of the refrigeration equipment is calculated as follows:

[0167]

[0168] Among them, E is the total energy consumption of refrigeration equipment, P i (t) is the power of the i-th device at time t, Q i (t) is the operating time of the i-th device, i is the device, and n is the total number of devices;

[0169] The total energy consumption of the refrigeration equipment of the new scheduling scheme is evaluated by the non-dominated sorting method (Pareto sorting) to generate the optimal scheduling strategy;

[0170] Specifically, each optimization scheduling scheme is ranked according to the total energy consumption and load satisfaction of the refrigeration equipment, and the optimal solution that is not "dominated" by other schemes is selected;

[0171] For multiple new scheduling schemes, evaluate the total energy consumption and balanced load satisfaction of the refrigeration equipment of each scheme, and finally determine the optimal scheduling strategy;

[0172] The final optimized scheduling strategy includes the specific start-up time, shutdown time, load ratio distribution and operating power of each device;

[0173] Generate the final optimal scheduling strategy under the premise of minimizing total energy consumption and satisfying load requirements;

[0174] It should be noted that by using the NSGA-II optimization algorithm to generate an optimized scheduling strategy based on the predicted value of the cooling load demand, efficient scheduling of the refrigeration equipment is achieved. On the premise of meeting the cooling load demand, the total energy consumption of the refrigeration equipment is minimized by optimizing the start-up time, shutdown time and load ratio distribution of the equipment. The combination of cross-simulation and variation simulation ensures the diversity and optimization of the scheduling scheme, significantly reduces energy consumption, improves the operating efficiency and reliability of the refrigeration, and ensures the long-term stable, economical and efficient operation of each equipment.

[0175] S4. Based on the optimized scheduling strategy, IoT is used to execute equipment startup and shutdown and load ratio distribution, and to monitor operating data in real time to dynamically adjust and optimize the operating status of the refrigeration equipment.

[0176] Furthermore, the startup time, shutdown time and load ratio distribution of the refrigeration equipment are extracted from the optimization scheduling strategy as control instructions;

[0177] Specifically, if device A is started in a certain time period (0, 1), the optimized scheduling strategy will clearly indicate that device A is started at time t=0;

[0178] If device A is started at a certain time period (0, 1), the shutdown time will indicate that device A is shut down at time t=1;

[0179] If device A accounts for 50% of the load in time period (0, 1), the optimized scheduling strategy will specify that the load proportion of device A in this time period is 0.5;

[0180] Establish connections between each refrigeration equipment and the Internet of Things through IoT;

[0181] Specifically, relevant sensors (such as temperature, humidity, pressure, and flow sensors) and controllers (such as programmable logic controllers (PLCs), intelligent controllers (IoT), and variable frequency controllers (VFDs)) are installed on each refrigeration equipment (such as compressors, cooling towers, and water pumps).

[0182] Connect various sensors and controllers to the refrigeration equipment via wired or wireless means to collect operating data and transmit control signals;

[0183] Choose the appropriate network connection method based on the specific situation of the refrigeration room, such as Wi-Fi, Ethernet, Zigbee, LoRa, or 5G communication;

[0184] Configure various sensors and controllers to the selected network and ensure that these devices can stably communicate with the IoT platform;

[0185] Install one or more IoT gateways in the refrigeration room to aggregate operating data from various sensors and controllers and transmit this operating data to the cloud or a central control center;

[0186] Select appropriate data transmission protocols, such as MQTT, HTTP, CoAP, etc., to ensure efficient transmission and security of operational data;

[0187] The control instructions for extracting the start-up time, shutdown time and load ratio distribution of the refrigeration equipment are sent to the corresponding refrigeration equipment through IoT to start, shut down and distribute the load ratio;

[0188] Use ambient temperature sensors, ambient humidity sensors, and equipment operating status monitors to collect operating data in real time;

[0189] The collected real-time operation data is transmitted and stored in the central control center via IoT;

[0190] The central control center uses the support vector machine algorithm to monitor the operating data in real time. When the operating data is abnormal, it indicates that the equipment has failed.

[0191] The central control center automatically sends alarms and initiates adjustments based on equipment failures;

[0192] If there is a slight abnormality, the load ratio distribution and temperature parameters of the refrigeration equipment will be automatically adjusted;

[0193] If there is a serious abnormality, start the backup refrigeration equipment;

[0194] Specifically, the historical operating data of the equipment under normal operating conditions is collected, including ambient temperature data, ambient humidity data, equipment status data, and historical load data;

[0195] Data is processed on historical operation data to remove noise and handle missing values ​​to ensure the quality of operation data;

[0196] Extract key features from operating data, such as extracting temperature change rate from ambient temperature data, extracting pressure fluctuation from pressure data in equipment status data, and extracting flow fluctuation from current and voltage data in equipment status data;

[0197] Construct a support vector machine model based on the support vector machine algorithm;

[0198] The extracted key features are divided into a training set and a test set. The training set is used to train the support vector machine model, and the test set is used to verify the performance of the support vector machine model.

[0199] Use support vector machine algorithms (such as linear SVM, radial basis kernel SVM, etc.) to train the support vector machine model and learn the characteristic patterns of normal operating conditions;

[0200] Real-time collection of equipment operation data, such as ambient temperature data, ambient humidity data, equipment status data and historical load data;

[0201] Standardize and extract features from real-time operation data and convert it into a format consistent with the training set;

[0202] Input real-time data into the trained support vector machine model for pattern matching and analysis;

[0203] The support vector machine model analyzes the input real-time operation data to determine whether it matches the normal operation mode;

[0204] When the support vector machine model detects that the input real-time data does not match the normal pattern, it is determined to be abnormal data;

[0205] According to the abnormal data characteristics, identify specific types such as temperature abnormality, pressure abnormality or flow abnormality;

[0206] Once the support vector machine model detects abnormal data, the central control center will immediately mark it and generate an abnormal event;

[0207] The central control center will send an immediate alarm notification to the designated management personnel or maintenance team via SMS, email, IoT applications (such as mobile apps), etc. The alarm content includes abnormal equipment, abnormality type and specific data indicators;

[0208] Automatically assess the severity of abnormal situations based on abnormal data and abnormal event types;

[0209] Minor abnormality adjustments include automatically adjusting the equipment's load ratio distribution, temperature settings and other parameters to restore normal operation, for example, adjusting the compressor's load and lowering the temperature;

[0210] Minor abnormalities have been adjusted to automatically start the backup equipment if the abnormality is serious to ensure uninterrupted cooling. For example, if equipment A fails, equipment B will be automatically started as a substitute.

[0211] Record all abnormal events and adjustment operations to ensure that subsequent maintenance and review can be traced back to the specific process;

[0212] It should be noted that the Internet of Things (IoT) is used to start and stop equipment and distribute loads, monitor equipment operating data in real time, implement dynamic adjustments, use support vector machine algorithms to monitor anomalies, and automatically adjust equipment load and temperature settings, or start backup equipment in the event of serious anomalies. This ensures efficient equipment operation, significantly reduces energy consumption and failures, and improves overall stability and reliability, providing comprehensive automated control and optimization solutions.

[0213] This embodiment also provides a high-efficiency refrigeration room performance optimization device, including: an acquisition module, a prediction module, an optimization module and a monitoring module; the acquisition module collects and preprocesses the operating data of the refrigeration equipment through multiple sensors; the prediction module constructs an MT-LSTM model based on the preprocessed operating data to predict future cooling load demand and generate a cooling load demand prediction value; the optimization module generates an optimized scheduling strategy based on the cooling load demand prediction value through the NSGA-II optimization algorithm; the monitoring module executes equipment startup and shutdown and load ratio distribution through the IoT according to the optimized scheduling strategy, monitors the operating data in real time, and dynamically adjusts and optimizes the operating status of the refrigeration equipment.

[0214] This embodiment also provides a computer device suitable for the case of a high-efficiency refrigeration room performance optimization method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the high-efficiency refrigeration room performance optimization method proposed in the above embodiment.

[0215] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0216] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for optimizing the performance of an efficient refrigeration room as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0217] In summary, the present invention achieves accurate demand forecasting by constructing an MT-LSTM model to predict future cooling load demand, which is important for optimizing the scheduling of refrigeration equipment. The MT-LSTM model can capture short-term, medium-term, and long-term dependency information and generate reliable cooling load demand forecasts by processing multiple feature data. In this way, even in the face of complex environmental changes and equipment operating conditions, the MT-LSTM model can still provide accurate demand forecasts, thereby avoiding over-cooling or under-cooling, improving the overall efficiency of refrigeration equipment operation, reducing unnecessary energy consumption, and ensuring that cooling load demand is accurately met.

[0218] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing the performance of a high-efficiency refrigeration room, characterized by: include, Collect and pre-process the operating data of refrigeration equipment through various sensors; Based on the preprocessed operating data, an MT-LSTM model is constructed to predict future cooling load demand and generate cooling load demand forecast values; Based on the cooling load demand forecast, the optimal scheduling strategy is generated by the NSGA-II optimization algorithm; Based on the optimized scheduling strategy, IoT is used to execute equipment startup and shutdown and load ratio distribution, and real-time monitoring of operating data is used to dynamically adjust and optimize the operating status of refrigeration equipment. The MT-LSTM model is constructed based on the pre-processed operating data to predict future cooling load demand and generate a cooling load demand prediction value. The specific steps are: Perform weighted fusion on the pre-processed running data to generate a unified data set; Divide the unified dataset into training set, validation set and test set; Build an MT-LSTM model based on LSTM, define the MT-LSTM model input as the training set, and the output as the cooling load demand forecast value; Extract the time series data from the training set, split it into multiple time periods according to the time steps of the time series data, form a time segment sequence, and input it into the multi-layer LSTM for processing; The first LSTM layer receives the time segment sequence, processes the time segment sequence through the gating mechanism, captures the short-term dependency information, and inputs it to the second LSTM layer; The second LSTM layer receives short-term dependency information, processes it through gating mechanisms and filtering, captures medium-term dependency information, and inputs it to the third LSTM layer; The third LSTM layer receives medium-term dependency information, combines the short-term dependency information of the first LSTM layer and the medium-term dependency information of the second LSTM layer through a gating mechanism, captures long-term dependency information, and outputs it to the fully connected layer; The fully connected layer receives and integrates short-term dependency information, medium-term dependency information, and long-term dependency information to calculate the cooling load demand forecast value, which is expressed as: ； in, is the cooling load demand forecast value, is the cooling load demand, is the predicted value, For the Ambient temperature data at a time point, For the Ambient humidity data at a time point, is the environment identifier, For the Equipment operating status data at a point in time, For the Historical load data at a time point, For time, is the total time; Use the validation set to evaluate the performance of the MT-LSTM model and adjust the parameters; The test set is used to measure the generalization ability and prediction accuracy of the MT-LSTM model.

2. The high-efficiency refrigeration room performance optimization method according to claim 1, characterized in that: The operating data of the equipment includes ambient temperature data, ambient humidity data, equipment status data and historical load data.

3. The high-efficiency refrigeration room performance optimization method according to claim 2, characterized in that: The preprocessing includes denoising, data normalization and missing value filling.

4. The high-efficiency refrigeration room performance optimization method according to claim 1, characterized in that: The optimization scheduling strategy is generated by the NSGA-II optimization algorithm based on the cooling load demand forecast value. The specific steps are: Select the NSGA-II optimization algorithm and define the optimization objective as minimizing the energy consumption of the refrigeration equipment; Set the start-up and shutdown times of multiple refrigeration devices according to the cooling load forecast value, and distribute the load proportions of multiple refrigeration devices; Convert the start-up time, shutdown time and load ratio distribution of each refrigeration equipment into chromosome code; Generate an initial scheduling plan based on chromosome encoding using the NSGA-II optimization algorithm; Optimize the initial scheduling plan through cross simulation and mutation simulation to generate a new scheduling plan; According to the new scheduling scheme, the total energy consumption of the refrigeration equipment is calculated as follows: ； in, is the total energy consumption of the refrigeration equipment, For the Devices at time The power, For the The running time of each device, For equipment, is the total number of devices; The total energy consumption of the refrigeration equipment in the new scheduling scheme is evaluated by the non-dominated sorting method to generate the optimal scheduling strategy.

5. The high-efficiency refrigeration room performance optimization method according to claim 4, characterized in that: The NSGA-II optimization algorithm is used to generate an initial scheduling plan based on chromosome coding. The specific steps are: Define the start time of chromosome encoding as a five-bit binary number to generate the initial chromosome; Define the closing time of chromosome encoding as a five-bit binary number to generate the initial chromosome; Define the load ratio of chromosome encoding as a four-bit binary number to generate the initial chromosome; The initial chromosomes of startup time, shutdown time and load ratio distribution are combined to generate encoding information; The coded information is disassembled and decoded to obtain the specific start-up time, shutdown time and load ratio distribution of each refrigeration equipment, and generate an initial scheduling plan.

6. The high-efficiency refrigeration room performance optimization method according to claim 1, characterized in that: According to the optimization scheduling strategy, the IoT is used to execute equipment startup and shutdown and load ratio distribution, and the operation data is monitored in real time to dynamically adjust and optimize the operation status of the refrigeration equipment. The specific steps are: Extracting the start-up time, shut-down time and load ratio distribution of refrigeration equipment from the optimization scheduling strategy as control instructions; Establish connections between each refrigeration equipment and the Internet of Things through IoT; The control instructions for extracting the start-up time, shutdown time and load ratio distribution of the refrigeration equipment are sent to the corresponding refrigeration equipment through IoT to start, shut down and distribute the load ratio; Use ambient temperature sensors, ambient humidity sensors, and equipment operating status monitors to collect operating data in real time; The collected real-time operation data is transmitted and stored in the central control center via IoT; The central control center uses the support vector machine algorithm to monitor the operating data in real time. When the operating data is abnormal, it indicates that the equipment has failed. The central control center automatically sends alarms and initiates adjustments based on equipment failures; If there is a slight abnormality, the load ratio distribution and temperature parameters of the refrigeration equipment will be automatically adjusted; If there is a serious abnormality, start the backup refrigeration equipment.

7. A high-efficiency refrigeration room performance optimization device, based on the high-efficiency refrigeration room performance optimization method according to any one of claims 1 to 6, characterized in that: Including, acquisition module, prediction module, optimization module and monitoring module; The acquisition module is used to collect the operating data of the refrigeration equipment through various sensors and perform pre-processing; The prediction module is used to build an MT-LSTM model based on the preprocessed operating data to predict future cooling load demand and generate a cooling load demand prediction value; The optimization module is used to generate an optimized scheduling strategy based on the cooling load demand forecast value through the NSGA-II optimization algorithm; The monitoring module is used to execute equipment startup and shutdown and load ratio distribution through IoT according to the optimized scheduling strategy, and to monitor operating data in real time to dynamically adjust and optimize the operating status of the refrigeration equipment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the high-efficiency refrigeration room performance optimization method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the high-efficiency refrigeration room performance optimization method according to any one of claims 1 to 6 are implemented.

Images