Energy efficiency optimization and fault diagnosis method, system, equipment, medium and program product based on the health of refrigeration room refrigeration machine combination

Abstract

The present application provides energy efficiency optimization and fault diagnosis methods, systems, equipment, media and program products based on the health of the refrigeration room refrigeration machine combination. The present application comprehensively considers multiple key indicators such as service life, failure rate and cooling capacity to conduct a comprehensive assessment of the health of the refrigeration machine; through normalization processing and reasonable weight coefficient determination, the evaluation result is more accurate and reflects the actual operating status of the refrigeration machine; potential problems of the refrigeration machine are discovered in time, early warning information is provided, maintenance and optimization strategies are guided, and the reliability and operating efficiency of the system are improved.

Description

Technical Field

[0001] The present application relates to the technical field of equipment health management, and in particular to energy efficiency optimization and fault diagnosis methods, systems, equipment, media and program products based on the health of a refrigeration room refrigeration machine combination. Background Art

[0002] In the refrigeration system, the chiller is the core equipment, and its operating status directly affects the energy efficiency and stability of the entire refrigeration system. The health of the chiller is not only related to the service life and operating cost of the equipment, but also has an important impact on the overall efficiency and reliability of the refrigeration system. Therefore, accurately assessing the health of the chiller is crucial to ensure the efficient and stable operation of the refrigeration system. Existing technologies usually only focus on a single parameter, such as the energy efficiency ratio (COP) or the failure rate of the equipment.

[0003] Energy efficiency ratio (COP) monitoring: Evaluate the operating efficiency and energy consumption of a chiller by monitoring its energy efficiency ratio (COP). The COP refers to the ratio of the chiller's cooling capacity to its power consumption, and is usually used to measure the energy efficiency performance of the equipment. However, the COP only reflects the energy efficiency level of the equipment under specific conditions, and it is difficult to fully evaluate the health of the chiller.

[0004] Failure rate analysis: By counting and analyzing the failure rate of the chiller, the reliability and stability of the equipment can be judged. Equipment with a high failure rate usually means that it has a greater operating risk and needs timely maintenance or replacement. However, simply relying on the failure rate to evaluate the health of the equipment cannot warn of potential problems in advance and cannot fully reflect the operating status of the equipment.

[0005] Regular maintenance and inspection: Ensure the normal operation of the equipment by regularly maintaining and inspecting the chiller. This method relies on experience and manual judgment, lacks quantitative analysis methods, has a certain lag, and cannot reflect the health status of the equipment in real time.

[0006] The existing technology has the following problems and deficiencies in the assessment of the health of refrigeration machines:

[0007] Single parameter dependence: Existing methods usually only focus on a single parameter, such as energy efficiency ratio or failure rate, and cannot comprehensively and comprehensively evaluate the health of the chiller. Single parameter evaluation methods tend to ignore other important operating indicators, resulting in one-sided and inaccurate evaluation results.

[0008] Lack of real-time performance: Although regular maintenance inspections can reveal some problems, they are lagging behind and cannot reflect the health status of the equipment in real time. If maintenance is performed after a failure occurs, it often causes certain losses, making it difficult to provide early warning and prevent potential failures.

[0009] Strong dependence on experience: Traditional evaluation methods rely on human experience and judgment, lacking scientific and objective quantitative analysis methods. Different operators may have different judgment criteria, and the evaluation results are highly subjective and uncertain.

[0010] Lack of comprehensive evaluation model: The existing technology lacks a comprehensive evaluation model that can combine multiple operating parameters to fully reflect the health of the chiller. Lack of comprehensive consideration of equipment operating life, failure rate, cooling performance and other aspects makes it difficult to provide a comprehensive and accurate health assessment.

[0011] Therefore, there are still certain technical challenges in the assessment of refrigeration machine health. There is a lack of methods to comprehensively assess the health of refrigeration machines, making it difficult to detect potential problems in a timely manner and optimize operating strategies. Summary of the invention

[0012] In view of the shortcomings of the prior art mentioned above, the purpose of this application is to provide energy efficiency optimization and fault diagnosis methods, systems, equipment, media and program products based on the health of the refrigeration room refrigeration machine combination. By comprehensively considering multiple key indicators such as service life, failure rate and cooling capacity, the health status of the refrigeration machine is quantitatively evaluated, providing a scientific basis for preventive maintenance and optimized operation, thereby solving the current technical problems of lack of methods for comprehensively evaluating the health status of refrigeration machines and difficulty in timely discovering potential problems.

[0013] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides an energy efficiency optimization and fault diagnosis method based on the health of a refrigeration room refrigeration machine combination, including: constructing an energy consumption target function and a health target function of a target refrigeration group; the energy consumption target function of the target refrigeration group is the sum of the energy consumption of all refrigeration machines in the target refrigeration group under preset working conditions; the health target function of the target refrigeration group is the sum of the health of all refrigeration machines in the target refrigeration group; wherein the health of each refrigeration machine is calculated by a set of relevant parameters; the set of relevant parameters includes multiple or all of the following parameters: current service life, failure rate, historical average cooling capacity, energy efficiency ratio, maintenance times; setting preset constraints, and iteratively optimizing the energy consumption target function and the health target function of the target refrigeration group based on a multi-objective optimization algorithm, so as to find the optimal refrigeration machine combination in the target refrigeration group that minimizes the total energy consumption of the target refrigeration group and maximizes the total health while meeting the current cooling demand.

[0014] In some embodiments of the first aspect of the present application, the health of each refrigerator is obtained by normalizing and weighting influencing factors such as current service life, failure rate, historical average cooling capacity, energy efficiency ratio, and maintenance times.

[0015] In some embodiments of the first aspect of the present application, the method also includes obtaining the weight coefficient of the refrigeration machine parameters through the hierarchical analysis method, and the process includes: decomposing the influencing factors of the refrigeration machine health into the target layer, the criterion layer and the scheme layer; constructing a judgment matrix through the pairwise comparison method, comparing the indicators in the same level in pairs, and determining the relative importance; calculating the eigenvalues ​​and eigenvectors of the judgment matrix to obtain the weights of each indicator.

[0016] In some embodiments of the first aspect of the present application, the energy consumption of each refrigerator in the target refrigeration unit under preset operating conditions is predicted by an energy consumption prediction model; the energy consumption prediction model is established based on the outlet water temperature and load rate of the refrigerator.

[0017] In some embodiments of the first aspect of the present application, the setting of preset constraints includes: setting selectivity and cooling demand constraints; the selectivity constraint is to select only turned-on refrigerators for optimization; the cooling demand constraint is to select an appropriate number of refrigerators in the refrigeration group to meet the current cooling demand.

[0018] In some embodiments of the first aspect of the present application, the process of iterating the multi-objective optimization algorithm includes: generating a set of initial solution sets representing different refrigeration machine configurations; calculating the total energy consumption and total health of each solution in the initial solution set to determine their fitness; performing selection, crossover and mutation operations based on the fitness evaluation results to generate a new solution set, simulating the natural selection process to explore more solution space; sorting the solution set using a non-dominated sorting method based on the total energy consumption and total health of each solution to identify the Pareto front solution set that strikes a balance between energy consumption and health; repeating all the above steps for iterative optimization until the algorithm converges to a set of optimal solutions.

[0019] In some embodiments of the first aspect of the present application, the method also includes: collecting and preprocessing real-time operating data of the refrigerator through sensors pre-installed at multiple key positions of the refrigerator; establishing health baseline data of the refrigerator based on the operating data of the refrigerator during a preset usage period; using a time series analysis method to monitor the real-time operating data of the refrigerator, and compare it with the health baseline data to diagnose faults of the refrigerator based on the comparison results.

[0020] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides an energy efficiency optimization and fault diagnosis system based on the health of a refrigeration room refrigeration machine combination, including: an objective function construction module, used to construct an energy consumption objective function and a health objective function of a target refrigeration group; the energy consumption objective function of the target refrigeration group is the sum of the energy consumption of all refrigeration machines in the target refrigeration group under preset working conditions; the health objective function of the target refrigeration group is the sum of the health of all refrigeration machines in the target refrigeration group; wherein the health of each refrigeration machine is calculated by a set of relevant parameters; the set of relevant parameters includes multiple or all of the following parameters: current service life, failure rate, historical average cooling capacity, energy efficiency ratio, maintenance times; a multi-objective optimization module, used to set preset constraints, and iteratively optimize the energy consumption objective function and health objective function of the target refrigeration group based on a multi-objective optimization algorithm, so as to find the best refrigeration machine combination in the target refrigeration group that minimizes the total energy consumption of the target refrigeration group and maximizes the total health while meeting the current cooling demand.

[0021] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the energy efficiency optimization and fault diagnosis method based on the health of the refrigeration room refrigeration machine combination.

[0022] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code is run on a computer, the computer implements the energy efficiency optimization and fault diagnosis method based on the health of the refrigeration room refrigeration machine combination.

[0023] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides a computer device, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the energy efficiency optimization and fault diagnosis method based on the health of the refrigeration room refrigeration machine combination.

[0024] As described above, the energy efficiency optimization and fault diagnosis method, system, device, medium and program product of the present application based on the health of the refrigeration room refrigeration machine combination have the following beneficial effects:

[0025] (1) Comprehensiveness: This application comprehensively considers multiple key indicators such as service life, failure rate and cooling capacity to conduct a comprehensive assessment of the health status of the chiller;

[0026] (2) Accuracy: Through normalization processing and determination of reasonable weight coefficients, the evaluation results are more accurate and reflect the actual operating conditions of the chiller;

[0027] (3) Early warning capability: timely detect potential problems of refrigeration equipment, provide early warning information, guide maintenance and optimization strategies, and improve system reliability and operating efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 Shown is a flow chart of an energy efficiency optimization and fault diagnosis method based on the health of a refrigeration room refrigeration machine combination in one embodiment of the present application.

[0029] Figure 2 Shown is a structural schematic diagram of an energy efficiency optimization and fault diagnosis system based on the health of a refrigeration machine combination in a refrigeration room in one embodiment of the present application.

[0030] Figure 3 Shown is a schematic diagram of the structure of a computer device in one embodiment of the present application. DETAILED DESCRIPTION

[0031] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0032] The technical solutions of the embodiments of the present application can be applied to various refrigeration systems, such as: compressor refrigeration system, absorption refrigeration system, thermoelectric refrigeration system, adsorption refrigeration system, centrifugal refrigeration system, screw refrigeration system, multi-split system, direct expansion refrigeration system, air source heat pump system, water-cooled refrigeration system, evaporative condenser system, chiller, etc.

[0033] To facilitate understanding of the embodiments of the present application, first Figure 1 Detailed description. Figure 1 The flowchart of a method for energy efficiency optimization and fault diagnosis based on the health of a refrigeration machine combination in a refrigeration machine room in an embodiment of the present invention is shown. The method for energy efficiency optimization and fault diagnosis based on the health of a refrigeration machine combination in a refrigeration machine room in this embodiment mainly includes the following steps:

[0034] Step S11: constructing an energy consumption target function and a health target function of a target refrigeration unit; the energy consumption target function of the target refrigeration unit is the sum of energy consumptions of all refrigeration units in the target refrigeration unit under preset working conditions.

[0035] It should be understood that the health objective function of the target refrigeration group is the sum of the health of all refrigeration machines in the target refrigeration group; wherein the health of each refrigeration machine is calculated by a set of relevant parameters; the set of relevant parameters includes multiple or all of the following parameters: current service life, failure rate, historical average cooling capacity, energy efficiency ratio, and number of maintenance times.

[0036] Preferably, the health of each chiller is calculated by normalizing the influencing factors such as current service life, failure rate, historical average cooling capacity, energy efficiency ratio, and maintenance times and then performing weighted sum calculation. An exemplary calculation formula is as follows:

[0037] Cooling machine health = k1×(1 / A) + k2×(1 / B) + k3×C + k4×D+ k5×(1 / E); Formula (1)

[0038] Among them, k1, k2, k3, k4, and k5 are weight coefficients, A represents the normalized current service life, B represents the normalized failure rate, C represents the normalized historical average cooling capacity, D represents the normalized energy efficiency ratio, and E represents the normalized maintenance times.

[0039] In the embodiment of the present application, the calculation formula of the normalized current service life is as follows:

[0040] Normalized current service life = current service life / normal service life; Formula (2)

[0041] It should be noted that the current service life and the normal service life are two different concepts. The normal service life refers to the length of time that the chiller is expected to operate normally under standard or expected working conditions. The current service life refers to the period of time that has passed since the chiller started operating. This length of time is an important indicator for measuring the degree of equipment aging and remaining service life. The normalized current service life has a value range between 0 and 1. The smaller the value, the shorter the remaining life of the equipment.

[0042] The length of normal service life is usually provided by the equipment manufacturer as an indicator of equipment performance. When the manufacturer is unable to provide service life parameter information, it can be estimated through industry standards or historical data. Based on the average service life data in industry standards and research reports as a reference, for example, the average service life of a chiller under normal conditions is usually between 10 and 15 years. Historical data estimation refers to collecting historical operating data of the same type of chillers and calculating the average service life through statistical analysis, such as using a company's internal chiller operation records or a public equipment failure and life database to calculate the average value. The calculation of the current service life begins at the time when the equipment is installed and first put into use. The current service life can be determined by the equipment's operating time record. This usually involves the cumulative equipment startup time, and may also include seasonal use or intermittent operation. The equipment's maintenance and repair records can help understand the changes in the equipment's condition during operation, which is very important for evaluating the current service life and predicting the remaining service life. Comparing the current service life with the normal service life provided by the manufacturer or industry standards can help assess whether the equipment is approaching its expected life cycle end.

[0043] In the embodiment of the present application, the calculation formula of the normalized current failure rate is as follows:

[0044] Normalized current failure rate = current failure rate / normal failure rate; Formula (3)

[0045] The normal failure rate is the expected failure rate of the chiller under standard or normal operating conditions. It is usually determined based on historical data, industry standards, or data provided by the manufacturer. The normal failure rate can be used as a benchmark for evaluating the performance and reliability of the equipment. The current failure rate is the actual failure rate of the chiller in a specific time period. It reflects the performance and reliability of the equipment in actual operation. The current failure rate can be calculated by counting the number of failures that occur within a specific time period.

[0046] Formula (3) above compares the current failure rate with the normal failure rate, and the resulting value can reflect the current failure rate relative to the normal level. The normalized value ranges from 0 to 1, and the smaller the value, the lower the failure rate of the device. Through normalization, it is easier to compare the failure rates of different devices or the same device in different time periods. The normalized failure rate can be used for performance monitoring, maintenance planning, and equipment update decisions.

[0047] In the embodiment of the present application, the calculation formula of the normalized historical average cooling capacity is as follows:

[0048] Normalized historical average cooling capacity = rated cooling capacity / historical average cooling capacity; Formula (4)

[0049] Rated cooling capacity refers to the standard cooling capacity set by the manufacturer for the chiller. It is the maximum cooling capacity that the equipment is designed to achieve under specific conditions. Historical average cooling capacity refers to the average cooling capacity calculated based on the historical data of the equipment in actual use, reflecting the performance of the equipment under actual operating conditions. The purpose of formula (4) above is to compare the historical average cooling capacity with the rated cooling capacity to obtain a proportional value, which can tell us the difference between the performance of the equipment in actual use and the design standard. The normalized value ranges from 0 to 1. The larger the value, the closer the equipment cooling output is to the rated value.

[0050] In the embodiment of the present application, the calculation formula of the normalized energy efficiency ratio is as follows:

[0051] Normalized energy efficiency ratio = actual energy efficiency ratio / standard energy efficiency ratio; formula (5)

[0052] The Coefficient of Performance (COP) of a chiller is an indicator to measure the efficiency of a chiller. It indicates the amount of cooling or heat generated by a chiller per unit of energy consumption. The higher the COP value, the better the energy efficiency of the chiller. The standard energy efficiency ratio refers to the energy efficiency ratio that a chiller should achieve under specific conditions, such as standard temperature and humidity. The actual energy efficiency ratio refers to the energy efficiency ratio of a chiller under actual operating conditions, which reflects the energy efficiency of the equipment in actual use. The normalized energy efficiency ratio has a value range between 0 and 1. The larger the value, the higher the energy efficiency of the equipment.

[0053] Normalized maintenance times = actual maintenance times / standard maintenance times; Formula (6)

[0054] Maintenance times refer to the number of maintenance and inspections performed on the chiller within a specific period of time. Maintenance times can reflect the operating status and maintenance needs of the equipment. Standard maintenance times refer to the expected maintenance times under normal use and maintenance conditions. They are usually based on the design life of the equipment, expected failure rate, or historical maintenance data. Actual maintenance times refer to the actual number of maintenance performed on the chiller during actual use due to various reasons (such as failures, regular inspections, or performance degradation). The normalized maintenance times have a value range between 0 and 1, and a larger value indicates more maintenance times.

[0055] In the embodiments of the present application, weight coefficients k1, k2, k3, k4, and k5 are obtained based on the expert experience method. The expert experience method is a qualitative analysis method that relies on the knowledge and experience of experts in the field. Experts make preliminary judgments on the importance of each indicator based on their understanding and experience of chiller operation. This method is simple and easy to implement, but may be affected by the subjective judgment of experts.

[0056] In the embodiments of the present application, weight coefficients k1, k2, k3, k4, and k5 are obtained based on the analytic hierarchy process. The analytic hierarchy process (AHP) is a multi-criteria decision-making method suitable for solving complex problems with a hierarchical structure. The advantage of the analytic hierarchy process is that it can handle complex multi-criteria decision-making problems and reduce the bias of subjective judgment by pairwise comparison. At the same time, the consistency check ensures the rationality of the decision-making process.

[0057] Specifically, the analysis process of the hierarchical analysis method includes: first, decomposing the factors affecting the health of the chiller into multiple levels such as the target level, the criterion level and the scheme level. Then, constructing the judgment matrix through the pairwise comparison method, comparing the indicators in the same level with each other to determine the relative importance. Next, calculating the eigenvalue and eigenvector of the judgment matrix to obtain the weight of each indicator. Finally, a consistency test is performed to ensure the rationality of the judgment matrix and avoid unreasonable weight distribution due to subjective judgment.

[0058] For example, to evaluate the health of a refrigerator, the key indicators to be considered include: current service life (A), failure rate (B), historical average cooling capacity (C), energy efficiency ratio (D), and maintenance times (E). The weight coefficient confirmation process is as follows:

[0059] Step 1: Establish a hierarchical model: This structural model includes the target layer, the criterion layer, and the solution layer. The target layer is the health of the refrigerator. The criterion layer is the current service life (A), failure rate (B), historical average cooling capacity (C), energy efficiency ratio (D), and maintenance times (E). The solution layer under each criterion layer (if any).

[0060] Step 2: Pairwise comparison and construction of judgment matrix: Compare each factor in the criterion layer pairwise, determine their relative importance, and give a score between 1 and 9. For example, if the current service life (A) is more important than the failure rate (B), fill in a number greater than 1 in the position of A relative to B, and finally form a matrix with five rows and five columns.

[0061] Step 3: Calculate weights: Calculate the eigenvalues ​​and eigenvectors of the judgment matrix to obtain the weight vectors of each criterion. For example, the weight vector of the above matrix can be: .

[0062] Step 4: Consistency test: Calculate the consistency index (CI) and random consistency index (RI), and then calculate the consistency ratio (CR) to ensure the rationality of the judgment matrix. If the CR is less than 0.1, the judgment matrix is ​​considered to have satisfactory consistency.

[0063] For example, the calculation formula of the consistency index (CI) is as follows: ; Formula (7); where, is the maximum eigenvalue of the judgment matrix, and n is the size of the judgment matrix (i.e., the number of rows or columns of the matrix).

[0064] For example, the random consistency index (RI) is determined based on the average consistency index of the random judgment matrix. It is related to the size of the judgment matrix. For matrices of different sizes, the RI value is pre-calculated. For example, the RI value of the third-order matrix is ​​0.58, the RI value of the fourth-order matrix is ​​0.90, the RI value of the fifth-order matrix is ​​1.12, etc. The consistency ratio (CR) is the ratio of CI to RI, which is used to test the consistency of the judgment matrix.

[0065] Step 5. Synthesize the total ranking: If there are sub-criteria or solution layers, the weight of the criterion layer needs to be synthesized with the weight of the sub-criteria layer to obtain the total weight of each solution, and then the solutions are ranked according to the total weight.

[0066] Step 6: Make a decision: Select the best performing solution or make a decision based on the total weight of the synthesis.

[0067] In an embodiment of the present application, weight coefficients k1, k2, k3, k4, and k5 are obtained based on a data-driven method. The data-driven method is a decision-making method based on data and algorithms, which relies on the analysis of historical data when determining the weight coefficients. The process of obtaining the weight coefficient based on the data-driven method generally includes: first, collecting all historical operating data related to the health of the chiller, including but not limited to energy consumption, failure rate, maintenance records, use environment, operating time, etc. Then, preprocessing the collected historical operating data, such as processing missing values ​​and outliers and standardizing or normalizing the data. Next, determine which indicators have a high correlation with the health of the chiller, for example, statistical methods (such as Pearson correlation coefficient) or feature selection algorithms can be used to identify key features. Subsequently, select a suitable statistical analysis model or machine learning model, such as regression analysis, decision tree, random forest, gradient boosting, neural network, etc. Use historical data to train the model and evaluate the impact of different indicators on the health of the chiller; adjust the model parameters and perform cross-validation to avoid overfitting. Finally, calculate the weight coefficient of each indicator based on the model results. For example, in a regression model, the size of the coefficient can reflect the importance of the indicator. Therefore, through the data-driven method, the impact of each indicator on the health of the chiller can be more objectively evaluated, and the accuracy and scientificity of the weight coefficient allocation can be improved. This method is particularly suitable for situations where data is abundant and the model can better capture the relationship between indicators.

[0068] In an embodiment of the present application, the energy consumption of each refrigerator in the target refrigeration unit under preset working conditions is predicted by an energy consumption prediction model; the energy consumption prediction model is built according to the outlet water temperature and load rate of the refrigerator. Assume that the energy consumption of the i-th refrigerator in the refrigeration unit under specific working conditions is Ei (T, L), and the total energy consumption is ΣEi (T, L). Assume that the health of the i-th refrigerator in the refrigeration unit is Hi, and the total health is ΣHi. The method for estimating the health of the refrigerator has been explained above and will not be repeated here.

[0069] It should be understood that the energy consumption prediction model Ei (T, L) of the chiller can predict the energy consumption of the chiller under different operating conditions by considering two key parameters: the outlet water temperature T and the load rate L. The outlet water temperature T directly affects the thermodynamic efficiency and heat exchange performance, while the load rate L reflects the workload of the compressor and the flow rate of the refrigerant, which together determine the energy consumption characteristics of the chiller. By analyzing the relationship between these two parameters and energy consumption, the operation of the chiller can be optimized to maximize energy efficiency, while providing decision support for system design, operation and maintenance, reducing energy consumption and improving economic and environmental sustainability.

[0070] Step S12: Set preset constraints, and iteratively optimize the energy consumption objective function and health objective function of the target refrigeration unit based on a multi-objective optimization algorithm, so as to find the optimal refrigeration unit combination in the target refrigeration unit that minimizes the total energy consumption and maximizes the total health of the target refrigeration unit while meeting the current cooling demand.

[0071] In the refrigeration system, each refrigeration unit has a health index and an energy consumption prediction model. In order to improve the overall performance of the system, when optimizing the energy efficiency of the refrigeration unit, in addition to minimizing energy consumption, it is also necessary to ensure that the selected refrigeration unit has the highest health. Therefore, there are two optimization goals in the embodiment of the present application:

[0072] Minimize energy consumption (Objective 1): Select one of the chillers in the chiller group for operation so that the total energy consumption of the chillers that are turned on under the current operating conditions is minimized.

[0073] Maximize health (Objective 2): Select a few of the chillers to operate so that the total health of the chillers is maximized.

[0074] They are to minimize the total energy consumption of the target refrigeration unit under the current operating conditions and to maximize the total health of this group of target refrigeration units.

[0075] In an embodiment of the present application, selectivity and cooling demand constraints are set, wherein the selectivity constraint refers to the switch state constraint of the refrigerator, and only the turned-on refrigerators are selected for optimization; the cooling demand constraint refers to selecting an appropriate number of refrigerators in the refrigeration unit to meet the current cooling demand.

[0076] Multi-objective optimization algorithms are a class of methods for solving optimization problems that contain multiple conflicting objectives. These algorithms find a balance point between multiple objectives, namely the Pareto Front, where no other solution is completely superior in all objectives. In the refrigeration machine optimization problem, the multi-objective optimization algorithm not only focuses on energy consumption, but also considers the health of the refrigeration machine.

[0077] In the embodiments of the present application, the multi-objective function includes but is not limited to: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Weighted Sum Method, Goal Programming, Pareto Optimization Method, Evolutionary Algorithm, etc.

[0078] Genetic Algorithm (GA) is a search algorithm that simulates the principles of natural selection and genetics. It is used to solve optimization and search problems. It iteratively improves solutions by simulating operations such as inheritance, crossover, and mutation in the process of biological evolution. Particle Swarm Optimization (PSO) is a swarm-based optimization algorithm that simulates the social behavior of bird flocks or fish schools to find the optimal solution. Particles fly in the search space and update their positions by tracking themselves and the best position in the group. The Weighted Sum Method converts multiple goals into a single objective function for optimization by setting different weights. Goal Programming sets an ideal value for each goal and optimizes each goal to be as close to its ideal value as possible. Pareto Optimization directly finds the Pareto frontier solution set without pre-setting the goal weight. Evolutionary Algorithms: Such as NSGA-II (Non-dominated Sorting Genetic Algorithm II) and SPEA2 (Strength Pareto Evolutionary Algorithm 2). These algorithms simulate the natural selection process to find a set of Pareto optimal solutions.

[0079] For example, the NSGA-II algorithm is used to illustrate the iterative optimization process: first, a set of initial solution sets representing different chiller configurations is generated; then, the total energy consumption and total health of each solution in the initial solution set are calculated to determine their fitness; then, selection, crossover and mutation operations are performed based on the fitness evaluation results to generate new solution sets, simulating the natural selection process to explore more solution spaces; then, non-dominated sorting is performed to identify the Pareto front solution set that achieves a balance between energy consumption and health; then, all the above steps are repeated for iterative optimization until the algorithm converges to a set of optimal solutions; finally, solutions that meet specific requirements are selected from the Pareto front to achieve the goals of minimizing energy consumption and maximizing health. This process is particularly suitable for dealing with multi-objective optimization problems, and can balance conflicting objectives and find the most comprehensive solution.

[0080] Explanatory, each solution in the initial solution set represents a possible chiller combination, including the number of chillers, models, operating parameters (such as outlet water temperature T and load rate L), etc. Fitness evaluation refers to calculating the total energy consumption and total health of each solution. The fitness function usually combines these two objectives and may use weighted sum or other methods to balance them. Selection, crossover and mutation refer to selecting solutions with better performance to enter the next generation according to the fitness evaluation results, which can usually be based on methods such as non-dominated sorting and crowding distance. By simulating the gene crossover process, some features of two or more solutions are combined to generate new solutions to explore the solution space. Small random changes are made to the solutions to introduce new genetic diversity to prevent the algorithm from falling into local optimality. Non-dominated sorting is to sort the solution set using the non-dominated sorting method according to the total energy consumption and total health of each solution. Solutions on the Pareto front in the solution set are considered non-dominated, that is, no other solutions are better than them in terms of energy consumption and health at the same time. Convergence to a set of optimal solutions means that as the iterations proceed, the algorithm gradually converges to a set of optimal solutions that achieve the best balance between energy consumption and health. These solutions constitute the final Pareto front. Finally, one or more solutions are selected from the Pareto front, which are selected based on actual needs and priorities. For example, if energy consumption is more important, the solution with the lowest energy consumption may be selected; if health is more important, the solution with the highest health may be selected.

[0081] Preferably, the technical solution of the embodiment of the present application also includes result display, which displays the health score and its changing trend through a visual interface to help users intuitively understand the comprehensive status of the chiller. Specifically, the visual interface includes the following elements: a real-time updated dashboard for displaying the current health score; a time series chart for displaying the change of the health score over time; a device comparison view that allows users to compare the health status of different devices; an alarm system for reminding users when the health score is below a threshold. The visual interface designed in this embodiment can select a suitable chart type to display data, for example, using a line chart to display the trend of the health score over time, using a bar chart to compare the health scores of different devices, etc. In order to improve the user experience, the visual interface can add interactive elements such as a time selector, a device selector, data filtering, etc., so that users can view data for a specific time period or a specific device according to their needs. The visual interface can also update data in real time so that users can see the latest health scores and changing trends. In addition, sufficient explanations and guidance are provided in the visual interface to help users understand the meaning of the score and the reasons behind the changing trend.

[0082] Preferably, the technical solution of the embodiment of the present application also includes warnings and suggestions. When the health score is lower than the preset threshold, the system automatically generates warning information and provides maintenance suggestions to guide users to perform equipment inspection and maintenance. Through such a warning and suggestion system, users can understand the health status of the equipment in a timely manner and take appropriate maintenance measures, thereby reducing unexpected downtime, extending the service life of the equipment, and improving overall operational efficiency.

[0083] Preferably, the energy efficiency optimization and fault diagnosis method based on the health of the refrigeration room refrigeration machine combination provided in the embodiment of the present application also includes: collecting and preprocessing the real-time operation data of the refrigeration machine through sensors pre-installed at multiple key positions of the refrigeration machine; establishing the health baseline data of the refrigeration machine based on the operation data of the refrigeration machine within a preset usage period; using a time series analysis method to monitor the real-time operation data of the refrigeration machine, and compare it with the health baseline data, so as to diagnose faults of the refrigeration machine based on the comparison results.

[0084] The sensors pre-installed in multiple key positions of the refrigerator mentioned here refer to high-precision sensors installed in key positions of the refrigerator. The preset positions include the inlet and outlet of the chilled water pipes, the inlet and outlet of the cooling water pipes, etc. of the refrigerator, which are used to monitor the inlet and outlet temperature of the chilled water, the inlet and outlet temperature of the cooling water, the chilled water flow rate, the cooling water flow rate, etc., to ensure that the installation position of the sensor can accurately reflect the actual operating status of the refrigerator.

[0085] The data acquisition system is used to collect, store and process data from various sensors, so as to monitor the operating status of the chiller in real time. The data acquisition system has a high sampling rate and stability, can continuously collect data from various sensors, can adapt to the harsh conditions of the industrial environment, and ensure the integrity and accuracy of the data. For example, it can be a PLC (programmable logic controller) with integrated data acquisition function, Modbus Muster, Raspberry Pi, etc.

[0086] The sensor data is transmitted to the central data processing server through a reliable communication protocol (such as Modbus TCP / IP, EtherCAT or Profinet, etc.). At the same time, in order to ensure the security and real-time nature of the data, data encryption technology and data redundancy technology are used during data transmission. Data encryption technology can use protocols such as SSL / TLS to encrypt the data transmission process to ensure that the data is not intercepted or tampered with during transmission; encrypt the data stored in the server or database to prevent unauthorized access, etc. Data redundancy technology includes regularly backing up data to different physical locations to ensure that the original data can be restored when it is lost or damaged; storing multiple copies of data on different servers or storage devices to improve data reliability and availability; using a distributed file system or database to store data on multiple nodes in a dispersed manner to reduce the risk of single point failures.

[0087] Furthermore, the data needs to be preprocessed:

[0088] First, outlier detection: Use statistical methods (such as Z-score or IQR) to identify and exclude outliers to prevent noise in the data from affecting subsequent analysis.

[0089] Secondly, data interpolation: For missing data, time series interpolation methods (such as linear interpolation or polynomial interpolation) can be used to fill them.

[0090] Finally, feature extraction: extract useful information from the raw data, such as temperature difference, pressure ratio, energy consumption rate, etc. These features help to more accurately evaluate the operating status of the chiller.

[0091] In the fault diagnosis stage, machine learning and data analysis techniques are used to identify the health status and potential faults of the chiller. The specific steps include:

[0092] First, establish a health baseline: Establish the health baseline data of the chiller based on the operating data of the chiller during the preset use period. For example, after the chiller is newly installed or overhauled, collect at least one month of normal operating data as the health baseline. This data will be used for subsequent comparative analysis to identify abnormal situations.

[0093] Second, anomaly detection: Use time series analysis methods (such as ARIMA, state space models, or deep learning models) to monitor real-time data streams, compare with baseline data, and identify fluctuations outside the normal range. It should be understood that time series analysis is a statistical technique used to model and predict data points arranged in time order. When monitoring real-time data streams, using time series analysis methods can help identify trends, seasonal patterns, and cyclical changes, thereby making effective forecasts and decisions.

[0094] Take ARIMA as an example: The principle of ARIMA (Autoregressive Integrated Moving Average) to monitor real-time data streams is to establish a mathematical model to predict future time points by analyzing the autocorrelation and non-seasonal patterns in historical data. The ARIMA model combines three main components: the autoregressive (AR) part captures the autocorrelation of the data; the difference (I) part is used to make non-stationary time series data stable; and the moving average (MA) part takes into account the random fluctuations of the data. By updating the model parameters in real time, ARIMA can adapt to new information in the data stream, thereby dynamically monitoring and predicting the data stream.

[0095] Finally, fault pattern recognition: Based on professional knowledge and preliminary data analysis, select the most discriminative feature set; use supervised learning algorithms (such as random forests, support vector machines, or deep neural networks) to train historical fault data to identify the characteristics of different fault modes; evaluate the accuracy and generalization ability of the model through cross-validation to ensure that the model can effectively predict faults on unknown data.

[0096] The above is a detailed explanation of the principle and implementation process of an energy efficiency optimization and fault diagnosis method based on the health of a refrigeration machine combination in a refrigeration room provided by the embodiment of the present application. To facilitate understanding by those skilled in the art, the following description is combined with specific scenarios.

[0097] Assume that a large refrigeration system contains 10 chillers. The health and energy consumption prediction model of each chiller is as follows:

[0098] Chiller 1: health level 90, energy consumption prediction model E1(T, L);

[0099] Chiller 2: health level 85, energy consumption prediction model E2 (T, L);

[0100] Chiller 3: health level 80, energy consumption prediction model E3 (T, L);

[0101] Chiller 4: health level 75, energy consumption prediction model E4 (T, L);

[0102] Chiller 5: health level 70, energy consumption prediction model E5 (T, L);

[0103] Chiller 6: health level 65, energy consumption prediction model E6 (T, L);

[0104] Chiller 7: health level 60, energy consumption prediction model E7 (T, L);

[0105] Refrigeration machine 8: health level 55, energy consumption prediction model E8 (T, L);

[0106] Chiller 9: health level 50, energy consumption prediction model E9 (T, L);

[0107] Chiller 10: Health level 45, energy consumption prediction model E10 (T, L).

[0108] The energy consumption prediction model Ei(T, L) of each chiller calculates its energy consumption based on the chiller's outlet water temperature T and load rate L.

[0109] The goal is to select an appropriate number of chillers based on the current cooling capacity required, so that the total energy consumption of the selected chillers is minimized and the total health is maximized.

[0110] First, define the objective function:

[0111] The total energy consumption is Etotal=ΣEi(T, L);

[0112] The total health is Htotal=ΣHi.

[0113] Secondly, determine the current operating conditions: determine the currently required cooling capacity Q and water outlet temperature T.

[0114] Finally, a multi-objective optimization algorithm is applied: the NSGA-II algorithm is used to find the Pareto frontier solution set through iteration and selection. In the solution set, a chiller combination that meets the cooling demand, has the lowest energy consumption and the highest health is selected.

[0115] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0116] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0117] like Figure 2 , a schematic diagram of the structure of an energy efficiency optimization and fault diagnosis system based on the health of a refrigeration machine combination in a refrigeration machine room according to an embodiment of the present invention is shown. The energy efficiency optimization and fault diagnosis system based on the health of a refrigeration machine combination in a refrigeration machine room 200 includes an objective function construction module 201 and a multi-objective optimization module 202.

[0118] The objective function construction module 201 is used to construct the energy consumption objective function and health objective function of the target refrigeration group; the energy consumption objective function of the target refrigeration group is the sum of the energy consumption of all refrigerators in the target refrigeration group under preset working conditions; the health objective function of the target refrigeration group is the sum of the health of all refrigerators in the target refrigeration group; wherein the health of each refrigerator is calculated by a set of related parameters; the set of related parameters includes multiple or all of the following parameters: current service life, failure rate, historical average cooling capacity, energy efficiency ratio, and number of maintenance times.

[0119] The multi-objective optimization module 202 is used to set preset constraints and iteratively optimize the energy consumption objective function and health objective function of the target refrigeration unit based on the multi-objective optimization algorithm, so as to find the optimal refrigeration unit combination in the target refrigeration unit that minimizes the total energy consumption and maximizes the total health of the target refrigeration unit while meeting the current cooling demand.

[0120] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here. It should also be understood that the division of modules in the embodiment of the present application is schematic, which is only a logical function division, and there may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application can be integrated into a processor, or it can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0121] Figure 3 is a schematic block diagram of a computer device provided in an embodiment of the present application. Figure 3 As shown in FIG. 1 , the computer device includes: at least one processor 301, a memory 302, at least one network interface 303 and a user interface 305. The various components in the device are coupled together through a bus system 304. It can be understood that the bus system 304 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 304 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 304 is not used in the embodiment of the present invention. Figure 3 In the specification, various buses are labeled as bus systems.

[0122] The user interface 305 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0123] It is understood that the memory 302 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable categories of memory.

[0124] The memory 302 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic terminal 300. Examples of these data include: any executable program used to operate on the electronic terminal 300, such as an operating system 3021 and an application 3022; the operating system 3021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 3022 may include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The energy efficiency optimization and fault diagnosis method based on the health of the refrigeration room refrigeration machine combination provided in the embodiment of the present invention may be included in the application 3022.

[0125] The method disclosed in the above embodiment of the present invention can be applied to the processor 301, or implemented by the processor 301. The processor 301 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit in the processor 301 or the instruction in the form of software. The above processor 301 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 301 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiment of the present invention. The general processor 301 can be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present invention, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0126] In an exemplary embodiment, the electronic terminal 300 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0127] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: a computer program code, when the computer program code is run on a computer, the computer executes Figure 1 The energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room in the illustrated embodiment.

[0128] According to the method provided in the embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program code, and when the program code is run on a computer, the computer executes Figure 1 The energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room in the illustrated embodiment.

[0129] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process, a processor, an object, an executable file, an execution thread, a program and / or a computer running on a processor. By way of illustration, both applications and computing devices running on a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes according to signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0130] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0131] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0132] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0133] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0135] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs)).

[0136] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0137] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0138] In summary, the present application provides a multi-objective optimized refrigeration unit management method, system, equipment, medium and program product. Through a multi-objective optimization algorithm, the present application can select a refrigeration unit combination with the lowest energy consumption and the highest health on the premise of meeting the current cooling demand, thereby improving the overall energy efficiency and reliability of the refrigeration system. Due to the introduction of health indicators, real-time monitoring of the refrigeration machine operation data and dynamic adjustment of the operation parameters according to the health assessment results can extend the service life of the equipment, reduce the failure rate, and optimize the maintenance strategy. Combined with the prediction model, potential failures can be warned in advance and the optimization strategy can be adjusted. At the same time, when evaluating the health, multiple key factors such as the current service life, failure rate, and cooling capacity are comprehensively considered to make a comprehensive assessment of the health of the refrigeration machine; through normalization processing and reasonable weight coefficient determination, the evaluation results are more accurate and reflect the actual operating conditions of the refrigeration machine. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0139] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. An energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room, characterized in that: include: Constructing an energy consumption objective function and a health objective function of a target refrigeration unit; the energy consumption objective function of the target refrigeration unit is the sum of the energy consumption of all refrigeration units in the target refrigeration unit under preset working conditions; the health objective function of the target refrigeration unit is the sum of the health of all refrigeration units in the target refrigeration unit; the energy consumption of each refrigeration unit in the target refrigeration unit under preset working conditions is predicted by an energy consumption prediction model; the energy consumption prediction model is constructed according to the outlet water temperature and load rate of the refrigeration unit; Among them, the health of each chiller = k1×(1 / A)+k2×(1 / B)+k3×C+k4×D+k5×(1 / E); k1, k2, k3, k4, k5 are weight coefficients, A represents the normalized current service life, B represents the normalized failure rate; C represents the normalized historical average cooling capacity; D represents the normalized energy efficiency ratio; E represents the normalized maintenance times; Setting preset constraints, and iteratively optimizing the energy consumption objective function and the health objective function of the target refrigeration unit based on a multi-objective optimization algorithm, so as to find the best refrigeration unit combination in the target refrigeration unit that minimizes the total energy consumption and maximizes the total health of the target refrigeration unit under the premise of meeting the current cooling demand; The real-time operating data of the refrigeration machine is collected and preprocessed by sensors pre-installed in multiple key positions of the refrigeration machine; the health baseline data of the refrigeration machine is established based on the operating data of the refrigeration machine within a preset usage period; the real-time operating data of the refrigeration machine is monitored using a time series analysis method and compared with the health baseline data, so as to diagnose faults of the refrigeration machine based on the comparison results.

2. The energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room according to claim 1 is characterized in that: The method also includes obtaining weight coefficients of refrigeration machine parameters through a hierarchical analysis method, and the process includes: decomposing the influencing factors of the health of the refrigeration machine into a target layer, a criterion layer and a scheme layer; constructing a judgment matrix through a pairwise comparison method, comparing indicators in the same layer in pairs to determine relative importance; calculating the eigenvalues ​​and eigenvectors of the judgment matrix to obtain the weights of each indicator.

3. The energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room according to claim 1 is characterized in that: The setting of preset constraints includes: setting selectivity and cooling demand constraints; the selectivity constraint is to select only the turned-on cooling machines for optimization; the cooling demand constraint is to select an appropriate number of cooling machines in the refrigeration unit to meet the current cooling demand.

4. The energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room according to claim 1 is characterized in that: The iterative process of the multi-objective optimization algorithm includes: Generate a set of initial solutions representing different chiller configurations; Calculating the total energy consumption and total health of each solution in the initial solution set to determine their fitness; Perform selection, crossover and mutation operations based on fitness evaluation results to generate new solution sets, simulating the natural selection process to explore more solution spaces; According to the total energy consumption and total health of each solution, the solution set is sorted using a non-dominated sorting method to identify the Pareto frontier solution set that achieves a balance between energy consumption and health; Repeat all the above steps for iterative optimization until the algorithm converges to a set of optimal solutions.

5. An energy efficiency optimization and fault diagnosis system based on the health of the refrigeration machine combination in the refrigeration room, characterized in that: include: The objective function construction module is used to construct the energy consumption objective function and health objective function of the target refrigeration unit; the energy consumption objective function of the target refrigeration unit is the sum of the energy consumption of all the refrigerators in the target refrigeration unit under the preset working conditions; the health objective function of the target refrigeration unit is the sum of the health of all the refrigerators in the target refrigeration unit; wherein the health of each refrigerator is calculated by a set of related parameters; the set of related parameters includes multiple or all of the following parameters: current service life, failure rate, historical average cooling capacity, energy efficiency ratio, maintenance times; the energy consumption of each refrigerator in the target refrigeration unit under the preset working conditions is predicted by the energy consumption prediction model; the energy consumption prediction model is built according to the outlet water temperature and load rate of the refrigerator A multi-objective optimization module is used to set preset constraints and iteratively optimize the energy consumption objective function and health objective function of the target refrigeration unit based on the multi-objective optimization algorithm, so as to find the best refrigeration unit combination in the target refrigeration unit that minimizes the total energy consumption and maximizes the total health of the target refrigeration unit under the premise of meeting the current cooling demand; collect and pre-process the real-time operation data of the refrigeration unit through sensors pre-placed in multiple key parts of the refrigeration unit; establish the health baseline data of the refrigeration unit based on the operation data of the refrigeration unit in the preset use period; The real-time operating data of the chiller is monitored by a time series analysis method and compared with the healthy baseline data, so as to perform fault diagnosis on the chiller according to the comparison result.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the energy efficiency optimization and fault diagnosis method based on the health of the refrigeration room refrigeration machine combination as described in any one of claims 1 to 4 is implemented.

7. A computer program product, characterized in that The computer program product includes computer program codes, and when the computer program codes are executed on a computer, the computer is enabled to implement the energy efficiency optimization and fault diagnosis method based on the health of a refrigeration machine combination in a refrigeration room as claimed in any one of claims 1 to 4.

8. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the energy efficiency optimization and fault diagnosis method based on the health of the refrigeration machine combination in the refrigeration room as described in any one of claims 1 to 4.

Images