A method, apparatus, device and medium for determining a refrigeration system fault

Abstract

The application discloses a refrigeration system fault determination method, device, equipment and medium, and relates to the technical field of refrigerator control. The scheme establishes a global fault diagnosis determination mode for the refrigeration system, converts the operation parameter fault determination problem of the refrigeration system into an operation parameter constraint optimization solving problem, considers the overall operation level of the refrigeration system, thereby avoiding the fault diagnosis of a single device of the refrigeration system, and is more suitable for actual engineering. The refrigeration system fault is positioned in a digital analysis mode, and the goals of reducing the operation energy consumption of the refrigeration system, guaranteeing the operation performance and safety of the system, guaranteeing the temperature requirement of a production process, and improving the equipment maintenance measurement and fault finding and repairing efficiency can be achieved.

Description

Technical Field

[0001] This application relates to the field of refrigeration control technology, and in particular to a method, apparatus, equipment and medium for determining faults in a refrigeration system. Background Technology

[0002] In most refrigeration systems, automatic control systems are commonly used to monitor and control the operating parameters of the refrigeration equipment. The main purpose is to achieve more efficient and energy-saving operation of the refrigeration system, as well as to ensure the temperatures required for production processes and create a healthy and comfortable building environment. Therefore, fault diagnosis of refrigeration system operating parameters is essential to ensure the normal operation of the refrigeration system.

[0003] While fault diagnosis of refrigeration system operating parameters is crucial for ensuring efficient system operation, existing fault diagnosis applications in practical engineering are not advanced enough. They primarily focus on individual devices within the system, independently detecting abnormal operating states of devices or the system as a whole through single parameters. This approach only fulfills the basic diagnostic objective of ensuring safe system operation, without fully considering the goals of improving refrigeration efficiency and reducing energy consumption.

[0004] Given the above problems, how to solve the problem of fault diagnosis in refrigeration systems that only focuses on diagnosing individual devices without considering the overall operating level of the refrigeration system is an urgent issue for technicians in this field. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, equipment and medium for determining faults in a refrigeration system, so as to solve the problem that fault diagnosis in a refrigeration system only targets the diagnosis of a single device and does not take into account the overall operating level of the refrigeration system.

[0006] To address the aforementioned technical problems, this application provides a method for determining faults in a refrigeration system, comprising:

[0007] Obtain the measured values ​​of the operating parameters of each module in the refrigeration system;

[0008] Obtain the pre-established constraint relationships and objective function among the operating parameters; wherein, the objective function characterizes a function that determines the failure probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter;

[0009] The objective function is solved based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimated values ​​of each operating parameter and its corresponding target failure probability.

[0010] Determine whether the probability of each target failure is less than the corresponding threshold.

[0011] If not, then it is confirmed that the module corresponding to the target failure probability is faulty.

[0012] Preferably, the process of establishing the constraint relationship between the operating parameters includes:

[0013] Obtain the correlation between the various operating parameters; wherein, the correlation includes at least the mass conservation relationship and the energy conservation relationship;

[0014] Establish the constraint relationships between the various operating parameters based on the aforementioned associations.

[0015] Preferably, the process of establishing the objective function includes:

[0016] The deviation threshold and the performance parameters of the measuring instrument for obtaining the operating parameters are described; wherein the deviation threshold characterizes the threshold at which a significant deviation occurs between the measured value and the estimated value of the operating parameters; and the performance parameters include at least an accuracy value.

[0017] The objective function is established based on the deviation threshold, the performance parameters, the measured values ​​of the operating parameters, and the estimated values.

[0018] Preferably, the step of solving the objective function based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimated values ​​of each operating parameter and its corresponding target failure probability includes:

[0019] An initial parent population is generated based on the measured values ​​of the operating parameters; wherein, individuals in the initial parent population represent the estimated values ​​of the operating parameters;

[0020] Obtain the individual fitness and the objective function value corresponding to each individual in the initial parent population, and take the individual whose individual fitness in the initial parent population meets the first preset requirement as the current estimated value;

[0021] Genetic operations are performed on the initial parent population to obtain the target offspring population;

[0022] Obtain the individual fitness and the objective function value corresponding to each individual in the target offspring population, and take the individual fitness of the target offspring population that meets the second preset requirement as the new estimated value, so as to update the current estimated value through the new estimated value;

[0023] Determine whether the preset number of iterations has been reached;

[0024] If not, return to the step of performing genetic operations on the initial parent population to obtain the target offspring population;

[0025] If so, the current estimate is used as the target estimate, and the objective function value is used as the target failure probability.

[0026] Preferably, obtaining the individual fitness of the individual includes:

[0027] A fitness function is constructed based on the constraints and the objective function; wherein the fitness function is a function that characterizes the degree to which the individual violates the constraints.

[0028] The individual fitness of the individual is obtained according to the fitness function.

[0029] Preferably, the genetic operation on the initial parent population to obtain the target offspring population includes:

[0030] The initial parent population is selected and replicated using a tournament method to obtain the initial offspring population.

[0031] Gene recombination is performed on the initial offspring population through a linear combination of crossover operators to obtain the gene-recombined offspring population.

[0032] The target offspring population is obtained by performing gene mutation operations on the offspring population after gene recombination through uniform mutation.

[0033] Preferably, after confirming that the module corresponding to the target failure probability has a failure, the method further includes:

[0034] Output the fault location, fault cause, and fault-related location of the module;

[0035] The operating parameters are corrected based on the target estimate corresponding to the module.

[0036] To address the aforementioned technical problems, this application also provides a refrigeration system fault determination device, comprising:

[0037] The first acquisition module is used to acquire the measured values ​​of the operating parameters of each module in the refrigeration system;

[0038] The second acquisition module is used to acquire the pre-established constraint relationship and objective function between the operating parameters; wherein, the objective function characterizes a function that determines the failure probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter;

[0039] The processing module is used to solve the objective function based on the measured values ​​of the operating parameters and the constraint relationship to obtain the target estimated value of each operating parameter and its corresponding target failure probability;

[0040] The judgment module is used to determine whether the probability of each target failure is less than the corresponding threshold; if not, the confirmation module is triggered.

[0041] The confirmation module is used to confirm that the module corresponding to the target failure probability has a failure.

[0042] To address the aforementioned technical problems, this application also provides a refrigeration system fault determination device, comprising:

[0043] Memory, used to store computer programs;

[0044] A processor is used to implement the steps of the above-described method for determining refrigeration system faults when executing the computer program.

[0045] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the aforementioned refrigeration system fault determination method.

[0046] The refrigeration system fault determination method provided in this application obtains the measured values ​​of the operating parameters of each module in the refrigeration system; obtains the pre-established constraint relationships and objective functions between the operating parameters; wherein, the objective function represents a function that determines the fault probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; solves the objective function based on the measured value and constraint relationship of the operating parameters to obtain the target estimated value of each operating parameter and its corresponding target fault probability; determines whether each target fault probability is less than the corresponding threshold; if not, confirms that the module corresponding to the target fault probability has a fault. Therefore, the above scheme establishes a global fault diagnosis and determination method for the refrigeration system, transforming the problem of determining the fault of the refrigeration system's operating parameters into a problem of optimizing the operating parameter constraints; it considers the overall operating level of the refrigeration system, thereby avoiding fault diagnosis of individual devices in the refrigeration system, and is more suitable for practical engineering. Locating refrigeration system faults through digital analysis can achieve the goals of reducing refrigeration system operating energy consumption, ensuring system operating performance and safety, ensuring the temperature requirements of production processes, and improving the efficiency of equipment maintenance measurement and fault finding and repair.

[0047] In addition, this application also provides a refrigeration system fault determination device, equipment and medium, with the same effect as above. Attached Figure Description

[0048] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart of a method for determining a refrigeration system fault is provided in an embodiment of this application;

[0050] Figure 2 A schematic diagram of a refrigeration system fault determination device provided in an embodiment of this application;

[0051] Figure 3 This is a schematic diagram of a refrigeration system fault determination device provided in an embodiment of this application. Detailed Implementation

[0052] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0053] The core of this application is to provide a method, apparatus, equipment and medium for determining faults in a refrigeration system, in order to solve the problem that fault diagnosis in a refrigeration system only targets a single device and does not take into account the overall operating level of the refrigeration system.

[0054] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] Fault diagnosis of refrigeration system operating parameters is crucial for ensuring efficient system operation. However, in practical engineering, existing fault diagnosis applications have limited diagnostic capabilities, primarily focusing on individual devices within the system and independently detecting abnormal operating states of devices or the system as a whole through single parameters. This only fulfills the basic diagnostic objective of ensuring safe system operation, without fully considering the goals of improving refrigeration efficiency and saving energy. Based on these issues, this application provides a method for determining faults in a refrigeration system. It should be noted that this application does not limit the application scenarios of the refrigeration system fault determination method; it can be applied to any scenario with a refrigeration system, depending on the specific implementation conditions.

[0056] Figure 1 This is a flowchart illustrating a method for determining a refrigeration system fault, as provided in an embodiment of this application. Figure 1 As shown, the method includes:

[0057] S10: Obtain the measured values ​​of the operating parameters of each module in the refrigeration system.

[0058] This application establishes a global parameter fault diagnosis model for refrigeration systems, transforming the problem of diagnosing operational parameter faults in refrigeration systems into a constrained optimization problem. In practical implementation, it is first necessary to determine the parameters that the parameter fault diagnosis model of the refrigeration system needs to monitor and diagnose, obtain relevant data indicators, and use the real-time measurement data of these indicators as input to the model. In this embodiment, the operational parameters corresponding to the measured values ​​in the refrigeration system are obtained, mainly including the operational parameters of the following modules:

[0059] (1) Operating parameters of the chiller unit;

[0060] Specifically, common operating parameters for a single chiller unit include:

[0061] chilled water inlet temperature T chw1 The unit is ℃;

[0062] Chilled water outlet temperature T chw2 The unit is ℃;

[0063] chilled water inlet pressure P chw1 The unit is MPa;

[0064] chilled water outlet pressure P chw2 The unit is MPa;

[0065] chilled water flow rate G chw The unit is m 3 / s;

[0066] Chilled water flow switch status F chw Where 0 represents the off state and 1 represents the on state;

[0067] Chilled water outlet electric valve switch status K chw Where 0 represents the off state and 1 represents the on state;

[0068] Cooling water inlet temperature T cw1 The unit is ℃;

[0069] Cooling water outlet temperature T cw2 The unit is ℃;

[0070] Cooling water inlet pressure P cw1 The unit is MPa;

[0071] Cooling water outlet pressure P cw2 The unit is MPa;

[0072] Cooling water flow rate G cw The unit is m 3 / s;

[0073] Cooling water flow switch status F cwWhere 0 represents the off state and 1 represents the on state;

[0074] Cooling water outlet electric valve switch status K cw Where 0 represents the off state and 1 represents the on state;

[0075] Compressor power (W) c The unit is kW.

[0076] (2) Operating parameters of the water pump;

[0077] Specifically, common monitoring parameters for water pumps in actual engineering projects include:

[0078] Import pressure P p1 The unit is MPa;

[0079] Export pressure P p2 The unit is MPa;

[0080] Water pump power (W) p The unit is kW;

[0081] Water pump frequency f p The unit is Hz;

[0082] The status of the electric valve at the water pump inlet is K1, where 0 indicates the closed state and 1 indicates the open state;

[0083] The status of the electric valve at the water pump outlet is K2, where 0 indicates the closed state and 1 indicates the open state.

[0084] When the pressure gauges measuring the inlet and outlet pressures are installed at the same horizontal height, the pressure difference between the inlet and outlet can be directly recorded as the pump head.

[0085] (3) Operating parameters of the cooling tower;

[0086] The operating status of a cooling tower is closely related to outdoor meteorological parameters, the status of the cooling tower fan, and the inlet and outlet conditions of the cooling water. Common monitoring parameters for cooling towers include:

[0087] outdoor air dry bulb temperature T db The unit is ℃;

[0088] outdoor air wet-bulb temperature T wb The unit is ℃;

[0089] Cooling tower outlet water temperature T w2 The unit is ℃;

[0090] Fan operating frequency f f The unit is Hz;

[0091] Fan operating power (W) fThe unit is kW;

[0092] Cooling water inlet electric valve K of the cooling tower w1 Where 0 represents the off state and 1 represents the on state;

[0093] Cooling tower cooling water outlet electric valve K w2 Where 0 represents the off state and 1 represents the on state;

[0094] The electric valves at the inlet and outlet of the cooling water in the cooling tower are designed to ensure that the cooling tower does not participate in the cooling water cooling process and to prevent phenomena such as backflow and bypass of the cooling water in the system.

[0095] (4) Operating parameters of the chilled water network;

[0096] The chilled water system connects the chilled side of the chiller unit, the water pumps, and the terminals. Its main operating parameters are:

[0097] chilled water supply main temperature T at the chiller plant side w1 The unit is ℃;

[0098] Chilled water return main water temperature T at the chiller plant w2 The unit is ℃;

[0099] User-side chilled water supply main water temperature T w1,s The unit is ℃;

[0100] The water temperature T in each chilled water return branch on the user side w2,s1 T w2,s2 And T w3,s2 The unit is ℃;

[0101] chilled water main flow rate G on the chiller plant side w The unit is m 3 / h;

[0102] Differential pressure ΔP of the manifold dc The unit is kPa;

[0103] Differential pressure bypass valve opening U dc The value range is 0 to 1.

[0104] (5) Operating parameters of the cooling water pipe network;

[0105] The main monitoring and operating parameters of the cooling water pipe network include:

[0106] High-temperature cooling water side main pipe water temperature T w1 The unit is ℃;

[0107] Low-temperature cooling water side main pipe water temperature T w2 The unit is ℃;

[0108] Cooling water main flow rate G w The unit is m 3 / h.

[0109] In this embodiment, the measured values ​​of the operating parameters of the above modules are obtained as the input of the model.

[0110] S11: Obtain the pre-established constraints and objective function between the running parameters.

[0111] The objective function is a function that determines the failure probability of a corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter.

[0112] Furthermore, the pre-established constraint relationships and objective functions among the operating parameters are obtained. In this application, the fault diagnosis problem of refrigeration system operating parameters is transformed into a constraint optimization problem with a common description.

[0113] The constraint relationships between operating parameters are constructed based on the correlations existing between system parameters. In specific implementations, the constraint relationships between parameters can be constructed through parameters related to the properties of the operating parameters themselves, including but not limited to the upper and lower limits of the measurement accuracy of the operating parameters, the state values ​​of the operating parameters under rated operating conditions, and the upper and lower limits of the values ​​of the operating parameters themselves; they can be constructed through the performance parameters of the refrigeration equipment, including but not limited to the range of cooling capacity load rate variation, the water-side pressure drop of the evaporator and condenser, the performance curve of the water pump, the frequency operating conditions of the water pump, and the heat exchange capacity of the cooling tower; they can also be constructed through the correlations between the various refrigeration system sub-modules, including but not limited to the relationship between the chilled water supply temperature of the chiller unit and the supply temperature of the chilled water main pipe of the chilled water network, and the relationship between the cooling water return temperature of the chiller unit and the water temperature of the low-temperature side main pipe of the cooling water network. In this embodiment, there are no restrictions on the method of constructing the constraint relationships between operating parameters, which depends on the specific implementation situation.

[0114] The optimization objective is determined based on constraint relationships. Specifically, the state values ​​of operating parameters are predicted and estimated. When the measured value of an operating parameter equals the corresponding estimated value, it indicates that the measured value of the operating parameter satisfies the constraints. When there is a deviation between the measured value and the corresponding estimated value, fault diagnosis is completed by analyzing the residuals. Therefore, the optimization objective of the parameter fault diagnosis model proposed in this application is based on the deviation between the estimated and measured values ​​of operating parameters, minimizing the characteristic variable representing the deviation or fault of the operating parameters. It should be noted that this characteristic variable can be the square of the deviation between the estimated and measured values ​​of the operating parameters, or the number of system parameter faults, etc., and is not limited in this embodiment.

[0115] Therefore, based on the above optimization objectives, the objective function can be obtained. The objective function characterizes the function that determines the failure probability of a corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter. Specifically, the n operating parameters to be diagnosed in the refrigeration system are denoted as the operating parameter vector M = [M1, M2, ..., M...]. n The optimization objective, inequality constraints, equality constraints, and upper and lower bound constraints of the parameters in the parametric fault diagnosis model are as follows:

[0116]

[0117] g k (M)≤0, k=1,2,...,s;

[0118] h j (M) = 0, j = 1, 2, ..., q;

[0119] M i,lb ≤M i ≤M i,ub , i = 1, 2, ..., n;

[0120] Among them, M' i M is the measured value of the running parameter i. i For the estimated value of the running parameter i, |M i -M' i | represents the absolute value of the deviation between the estimated and measured values ​​of operating parameter i, f i (|M i -M' i |) represents the probability function for estimating parameter failures based on deviations in measured operating parameters, i.e., the objective function; g k (M)≤0 represents the k-th inequality constraint, and s represents the number of inequality constraints; h j (M) = 0 represents the j-th equality constraint, q represents the number of equality constraints, and M i,lb ≤M i ≤M i,ub For parameter M i The upper and lower limits of the value.

[0121] Therefore, the physical meaning of the parametric fault diagnosis model is: by estimating the measured values ​​of operating parameters, to find a set of estimated values ​​that minimizes the sum of the failure probabilities of the refrigeration system while satisfying the constraints. In this embodiment, the construction process of the objective function is not limited and depends on the specific implementation.

[0122] S12: Solve the objective function based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimated values ​​of each operating parameter and its corresponding target failure probability.

[0123] After obtaining the measured values ​​of the operating parameters and the objective function, the objective function is solved based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimated values ​​of each operating parameter and their corresponding target failure probabilities. This embodiment does not impose restrictions on the solution process of the objective function; it depends on the specific implementation.

[0124] S13: Determine whether the failure probability of each target is less than the corresponding threshold; if not, proceed to step S14.

[0125] S14: Confirm that the module corresponding to the target failure probability is faulty.

[0126] Finally, after solving the objective function to obtain the target estimates of the operating parameters and their corresponding target failure probabilities, it is determined whether each target failure probability is less than the corresponding threshold. It should be noted that this embodiment does not impose a limit on the size of the threshold; it depends on the specific implementation.

[0127] When the probability of a target fault is confirmed to be less than the corresponding threshold, the deviation between the estimated and measured values ​​of the corresponding operating parameter is small, indicating that the module to which the operating parameter belongs is not faulty, and the process can return to S10 to continue acquiring measured values ​​for the next round of fault diagnosis. When the probability of a target fault is confirmed to be not less than the corresponding threshold, the deviation between the estimated and measured values ​​of the corresponding operating parameter is large, indicating that the module to which the operating parameter belongs is faulty. The user can choose to directly repair the measurement parameter error online through the automatic control system of the refrigeration system, or choose to output information such as the fault location and fault rate to guide offline repair. In this way, the fault diagnosis process of the refrigeration system operating parameters is realized.

[0128] In this embodiment, the measured values ​​of the operating parameters of each module in the refrigeration system are obtained; the pre-established constraint relationships and objective functions between the operating parameters are acquired; wherein, the objective function characterizes the function that determines the fault probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; the objective function is solved based on the measured value and constraint relationship of the operating parameters to obtain the target estimated value of each operating parameter and its corresponding target fault probability; it is determined whether each target fault probability is less than the corresponding threshold; if not, it is confirmed that the module corresponding to the target fault probability has a fault. Therefore, the above scheme establishes a global fault diagnosis and determination method for the refrigeration system, transforming the problem of determining the fault of the operating parameters of the refrigeration system into a problem of optimizing the operating parameter constraints; it considers the overall operating level of the refrigeration system, thereby avoiding fault diagnosis of individual devices in the refrigeration system, and is more suitable for practical engineering. Locating refrigeration system faults through digital analysis can achieve the goals of reducing refrigeration system operating energy consumption, ensuring system operating performance and safety, ensuring the temperature requirements of production processes, and improving the efficiency of equipment maintenance measurement and fault finding and repair.

[0129] Based on the above embodiments, in some embodiments, the process of establishing the constraint relationship between operating parameters includes:

[0130] S110: Obtain the correlation between various operating parameters.

[0131] Among them, the correlation includes at least the mass conservation relationship and the energy conservation relationship.

[0132] S111: Establish constraint relationships between various operating parameters based on the association relationships.

[0133] Specifically, to establish constraints between operating parameters, the correlations between various operating parameters are first obtained, and then constraints are established based on these correlations. For example, a relationship between flow rate parameters is established based on the mass conservation principle; a relationship between temperature and flow rate is established based on the energy conservation principle. Furthermore, more relationships between parameters can be established based on prior knowledge, the physical processes of the air conditioning system, and the performance of the air conditioning system equipment, etc., which are not limited in this embodiment. The following uses a chiller unit as an example to illustrate the construction of constraints between its operating parameters:

[0134] (1) Inequality constraint relationship

[0135]

[0136] Among them, the above inequality constraint relationship characterizes the range of variation of the cooling capacity of the chiller unit, PLR lb PLR ub and These are the upper and lower limits of the load rate and the rated cooling capacity, respectively, both of which are known information.

[0137]

[0138]

[0139]

[0140]

[0141] In the above inequalities, g3 and g4 correspond to the range of variation of the actual evaporator temperature of the chiller unit relative to its rated value, and g5 and g6 correspond to the range of variation of the actual condenser temperature of the chiller unit relative to its rated value; T e T is the evaporation temperature. c This is the condensation temperature; and These are the evaporator approach temperature rating and the condenser approach temperature rating, respectively; k lb and k ubThese are the upper and lower limits of the ratio between the actual approach temperature and the rated approach temperature, respectively.

[0142] (2) Equality constraint relationship

[0143] T cw1 =T cw1,p ;

[0144] The above equation characterizes the inlet water temperature T of the chiller unit. cw1 Equal to the cooling water supply (from the cooling tower to the chiller) main pipe water temperature T cw1,p .

[0145]

[0146] The above equation represents the chilled water inlet pressure P of the chiller unit. chw1 Slightly less than the chilled water pump outlet pressure P p2,ch Considering the hydraulic pressure drop along the pipe section from the chilled water pump to the chiller unit.

[0147] (3) Constraints on the range of operating parameters

[0148]

[0149]

[0150] The aforementioned constraints characterize the operating range of the actual chilled water flow rate and cooling water flow rate relative to their respective rated flow rates. For a constant flow system, k G,lb and k G,ub Approaching 1, possible values ​​are 0.9 and 1.1; for variable flow systems, k G,lb and k G,ub The value is determined based on the performance of the variable flow chiller unit.

[0151] T hchw,lb ≤T chw1 ≤T hchw,ub ;

[0152] T lchw,lb ≤T chw2 ≤T lchw,ub ;

[0153] The aforementioned constraint relationship characterizes the range of temperature variation of the chilled water supply and return water of the chiller unit, T hchw,lb and T hchw,ub These are the upper and lower limits of the chilled water inlet supply temperature, T. lchw,lb and T lchw,ubThese are the upper and lower limits of the chilled water outlet supply temperature, respectively. The chilled water supply temperature is affected by the user's load demand and actual usage. The chilled water return temperature affects the performance of the chiller unit and is usually taken as 9 to 15°C.

[0154] It should be noted that the constraints between the operating parameters of the chiller unit include, but are not limited to, the relationships described above. The examples in this embodiment are merely illustrative.

[0155] Based on the above embodiments, as a preferred embodiment, the process of establishing the objective function includes:

[0156] S112: Performance parameters of measuring instruments for obtaining deviation thresholds and operating parameters.

[0157] Among them, the deviation threshold characterizes the threshold at which the measured and estimated values ​​of the operating parameters deviate significantly; the performance parameters include at least the accuracy value.

[0158] S113: Establish the objective function based on the deviation threshold, performance parameters, and measured and estimated values ​​of operating parameters.

[0159] Specifically, the deviation threshold and performance parameters of the measuring instruments used for operation are obtained. The deviation threshold represents the threshold at which a significant deviation occurs between the measured and estimated values ​​of the operating parameters; the performance parameters include at least an accuracy value. Furthermore, an objective function is established based on the deviation threshold, performance parameters, and the measured and estimated values ​​of the operating parameters. The details are as follows:

[0160]

[0161] Among them, e i,1 The accuracy of the measuring instruments for operating parameters; e i,2 To determine the lower limit for significant deviations in operating parameters, its value is related to the algorithm's sensitivity to parameter measurement deviations, that is, the system's tolerance to parameter deviations.

[0162] As can be seen from the objective function above, when the deviation of the operating parameters is no greater than the measurement accuracy e i,1 When the parameter deviation exceeds e, it is considered that the operating parameters have not experienced significant errors; when the parameter deviation exceeds e, it is considered that the operating parameters have not experienced significant errors. i,2 When the parameter deviation is within e, it is assumed that a significant error will occur; when the parameter deviation is within e... i,1 With e i,2 When the parameters are within a certain range, a significant error in the operating parameters is considered a probabilistic event. It should be noted that, depending on the performance of the measuring instrument and the nature of the parameters, the probability expression can be varied; in this embodiment, it is specifically set as a linear function.

[0163] Since the optimization objective of the parametric fault diagnosis model is global optimum, optimizations that rely on a single initial value (such as the steepest descent method) are prone to getting trapped in local optima and are therefore unsuitable. In contrast, the genetic algorithm, as an intelligent algorithm, does not require specific forms of the objective function, such as whether it is differentiable or continuous, and it starts its search based on multiple initial values ​​in the search space. It is suitable for nonlinear optimization problems, helps avoid getting trapped in local optima, and is more likely to achieve global optimum.

[0164] Therefore, based on the above embodiments, as a preferred embodiment, this embodiment utilizes a genetic algorithm to solve the parameter fault diagnosis model. The objective function is solved based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimated values ​​of each operating parameter and their corresponding target fault probabilities, including:

[0165] S120: Generate the initial parent population based on the measured values ​​of the operating parameters.

[0166] Among them, the estimated values ​​of the individual representation running parameters in the initial parent population.

[0167] Specifically, based on the measured values ​​of each operating parameter, the estimated values ​​of the corresponding refrigeration system operating parameters are randomly generated, and the parameter indicators are marked in the form of real number encoding, thereby generating p individuals to form the initial parent population of the genetic algorithm model.

[0168] S121: Obtain the individual fitness and the corresponding objective function value of each individual in the initial parent population, and take the individual whose fitness in the initial parent population meets the first preset requirement as the current estimated value.

[0169] The fitness of each individual in the initial parent population is further calculated to evaluate the probability of refrigeration system failure under various combinations of operating parameters, i.e., the objective function value. Individuals whose fitness meets a first preset requirement are used as the initial solution of the model, i.e., the current estimated value. In this embodiment, the first preset requirement is not limited and depends on the specific implementation. In some embodiments, when an individual's fitness is optimal, it can be considered to meet the first preset requirement. Furthermore, the calculation process of individual fitness is not limited in this embodiment and depends on the specific implementation.

[0170] It is important to note that individual fitness is an indicator used to evaluate and select individuals based on their merits. For infeasible individuals, a penalty function method is typically used, applying a penalty factor to the original objective function to account for the degree to which the infeasible solution violates constraints. Therefore, the penalty function method can be used to combine constraints and the objective function to construct a fitness function for evaluating individuals. Thus, in some embodiments, obtaining the individual fitness includes:

[0171] S1210: Construct the fitness function based on the constraints and the objective function.

[0172] The fitness function is a function that characterizes the degree to which an individual violates the constraints.

[0173] S1211: Obtain the individual fitness of an individual based on the fitness function.

[0174] Specifically, the fitness function is constructed as follows:

[0175]

[0176] Where, x i Let the decision variable vector be x = [x1, x2, ..., xn]. n ], which is equivalent to the runtime parameter vector M = [M1, M2, ..., M n ];

[0177] g i (x)≤0; indicates that the decision variables need to satisfy the inequality constraints;

[0178] h j (x) = 0; indicates that the decision variables need to satisfy the equality constraint;

[0179] i = 1, 2, ..., m; represents the degree to which the decision variable violates the inequality constraint;

[0180] i = 1, 2, ..., k; represents the degree to which the decision variable violates the equality constraint;

[0181] It indicates the maximum extent to which a decision variable violates the constraints.

[0182] Therefore, the individual fitness value of each individual can be calculated, and individuals with higher fitness values ​​correspond to better objective function values. Based on the principle of survival of the fittest, individuals with higher fitness are more likely to be selected and pass on superior genes to their offspring through genetic manipulation.

[0183] S122: Perform genetic operations on the initial parent population to obtain the target offspring population.

[0184] Further genetic manipulations were performed on the initial parent population. These manipulations primarily included selection for replication, gene recombination, and gene mutation. The genetic manipulations are described in detail below:

[0185] As a preferred embodiment, genetic operations are performed on the initial parent population to obtain the target offspring population, including:

[0186] S1220: Selective replication is performed on the initial parent population using a tournament method to obtain the initial offspring population.

[0187] Selection-based replication refers to a mechanism that selects individuals with higher fitness and eliminates those with lower fitness to obtain an initial offspring population with higher overall fitness. In this embodiment, the tournament selection method is used as the selection operator.

[0188] Specifically, a tournament-style selection process is used to select and replicate the initial parent population: m individuals are randomly selected from p combinations of refrigeration system operating parameters, and the individual with the highest fitness is extracted from these. This process is repeated M times to generate M optimal combinations of operating parameters. Thus, individuals with high fitness are selected and their superior genes are passed on to offspring through genetic operations, generating the initial offspring population.

[0189] S1221: Gene recombination is performed on the initial offspring population through a linear combination of crossover operators to obtain the gene-recombined offspring population.

[0190] Gene recombination involves randomly pairing individuals from the initial offspring population and determining, based on the crossover probability, whether the two paired initial offspring individuals will undergo gene recombination to generate two new offspring. In this embodiment, arithmetic crossover is used as the crossover operator.

[0191] Specifically, arithmetic crossover generates new individuals by linearly combining two individuals. The specific operation is as follows: two distinct initial offspring individuals p1 and p2 are randomly selected, and a random number r within the interval [0,1] is generated. When r does not exceed the crossover probability p... c At that time, two individuals undergo arithmetic crossover using the following formula:

[0192] S c1 =u c ×p1+(1-u c )×p2;

[0193] S c2 =(1-u c )×p1+u c ×p2;

[0194] Among them, u c S is a proportionality coefficient, randomly generated within the interval [0,1]. c1 and S c2 For newly generated offspring individuals.

[0195] Therefore, through gene recombination, a better combination of operating parameters for the refrigeration system can be generated based on superior genes, resulting in a solution with a lower failure rate for the refrigeration system operating parameters.

[0196] S1222: Perform gene mutation operations on the offspring population after gene recombination through uniform mutation to obtain the target offspring population.

[0197] Genetic mutation refers to the low-probability mutation of certain genes in individuals within a population, resulting in new individuals. Mutation, by introducing new genes, helps prevent the population from getting trapped in local optima and converging prematurely. The mutation probability is very low; if it is too high, the genetic algorithm will become a random probability search method, leading to non-convergence and continuous oscillations. Therefore, this embodiment uses a uniform mutation operator.

[0198] Uniform mutation refers to replacing the values ​​of all gene loci in an individual with a relatively small probability using random numbers uniformly distributed within a certain range. Specifically, for an individual p, a random number r is generated within the interval [0,1]. When r does not exceed the mutation probability p... m At that time, generate a random number u in the range [0, 0.5]. m Then, the mutated new individual is obtained according to the following formula:

[0199] s m =(1+u m )×p;

[0200] Among them, u m s is the proportionality coefficient. m For the mutated individual.

[0201] This leads to the derivation of the target offspring population for the final operating parameters of the refrigeration system.

[0202] S123: Obtain the individual fitness and the corresponding objective function value of each individual in the target offspring population, and take the individual fitness of the target offspring population that meets the second preset requirement as the new estimated value, so as to update the current estimated value with the new estimated value.

[0203] Furthermore, after the initial parent population undergoes selection, replication, gene recombination, and gene mutation to generate a new target offspring population, the individual fitness and the corresponding objective function value of each individual in the target offspring population are obtained. At the same time, individuals in the target offspring population whose fitness meets the second preset requirement are used as new estimated values ​​to update the current estimated value.

[0204] It should be noted that this embodiment does not impose any restrictions on the second preset requirement, but rather depends on the specific implementation. In some embodiments, the second preset requirement is considered to be satisfied when the individual fitness of an individual is optimal.

[0205] S124: Determine whether the preset number of iterations has been reached; if not, return to step S122; if yes, proceed to step S125.

[0206] S125: Use the current estimate as the target estimate and the objective function value as the target failure probability.

[0207] After obtaining the estimated values ​​of the new operating parameters, a decision is made on whether to continue the iteration. Specifically, if the objective function value corresponding to the optimal individual in the target offspring population is greater than the set fault probability, and the current iteration count is less than the preset iteration count, then the process returns to step S122 to continue the iteration. If the objective function value corresponding to the optimal individual in the target offspring population is less than or equal to the set fault probability, or the current iteration count is greater than or equal to the preset iteration count, then the iteration stops. At this point, the best individual in the target offspring population is the optimal solution to the optimization problem, meaning the current estimated value is used as the final target estimated value, and the objective function value at this point is used as the target fault probability. This achieves the solution of the parameter fault diagnosis model.

[0208] Based on the above embodiments, as a preferred embodiment, after confirming that the module corresponding to the target failure probability has a failure, the method further includes:

[0209] S15: Fault location, fault cause, and fault-related location of the output module.

[0210] S16: Correct the operating parameters based on the target estimate corresponding to the module.

[0211] Specifically, after the algorithm stops iterating, the overall failure rate of the refrigeration system, the parameter failure rate of each submodule, and the optimal estimated operating parameters can be obtained. For modules with high failure rates, system users can choose to directly repair measurement parameter errors online through the refrigeration system's automatic control system, or they can choose to output information such as the fault location, cause of the fault, and related fault locations of the module, and further correct the operating parameters based on the target estimated values ​​corresponding to the module, thereby achieving fault repair.

[0212] In the above embodiments, the method for determining refrigeration system faults has been described in detail. This application also provides embodiments of the refrigeration system fault determination device.

[0213] Figure 2 This is a schematic diagram of a refrigeration system fault determination device provided in an embodiment of this application. Figure 2 As shown, the refrigeration system fault determination device includes:

[0214] The first acquisition module 10 is used to acquire the measured values ​​of the operating parameters of each module in the refrigeration system.

[0215] The second acquisition module 11 is used to acquire the pre-established constraint relationship and objective function between operating parameters; wherein, the objective function represents the function that determines the failure probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter.

[0216] The processing module 12 is used to solve the objective function based on the measured values ​​of the operating parameters and the constraint relationships, so as to obtain the target estimated value of each operating parameter and its corresponding target failure probability.

[0217] The judgment module 13 is used to determine whether the failure probability of each target is less than the corresponding threshold; if not, the confirmation module 14 is triggered.

[0218] The confirmation module 14 is used to confirm that the module corresponding to the target failure probability has a failure.

[0219] In this embodiment, the refrigeration system fault determination device includes a first acquisition module, a second acquisition module, a processing module, a judgment module, and a confirmation module. The refrigeration system fault determination device can implement all the steps of the above-described refrigeration system fault determination method during operation. It acquires the measured values ​​of the operating parameters of each module in the refrigeration system; acquires the pre-established constraint relationships and objective functions between the operating parameters; wherein the objective function characterizes the function that determines the fault probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; solves the objective function based on the measured value and constraint relationships of the operating parameters to obtain the target estimated value of each operating parameter and its corresponding target fault probability; determines whether each target fault probability is less than the corresponding threshold; if not, confirms that the module corresponding to the target fault probability has a fault. Therefore, the above solution establishes a global fault diagnosis and determination method for the refrigeration system, transforming the problem of determining the fault of the refrigeration system's operating parameters into a problem of optimizing the operating parameter constraints; it considers the overall operating level of the refrigeration system, thereby avoiding fault diagnosis of individual devices in the refrigeration system, and is more suitable for practical engineering. By using digital analysis to locate faults in the refrigeration system, it is possible to achieve the goals of reducing the energy consumption of the refrigeration system, ensuring the performance and safety of the system, ensuring the temperature requirements of the production process, and improving the efficiency of equipment maintenance, measurement, fault finding and repair.

[0220] Figure 3 This is a schematic diagram of a refrigeration system fault determination device provided in an embodiment of this application. Figure 3 As shown, the equipment for determining refrigeration system faults includes:

[0221] Memory 20 is used to store computer programs.

[0222] The processor 21 is used to execute a computer program to implement the steps of the refrigeration system fault determination method mentioned in the above embodiments.

[0223] The refrigeration system fault determination device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0224] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0225] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 20 is used to store at least the following computer program 201, which, after being loaded and executed by the processor 21, is capable of implementing the relevant steps of the refrigeration system fault determination method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, and the storage method may be temporary or permanent storage. The operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, the data involved in the refrigeration system fault determination method.

[0226] In some embodiments, the refrigeration system fault determination device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0227] Those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the device for determining refrigeration system faults and may include more or fewer components than shown.

[0228] In this embodiment, the refrigeration system fault determination device includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the steps of the refrigeration system fault determination method mentioned in the above embodiment. This involves acquiring measured values ​​of the operating parameters of each module in the refrigeration system; acquiring pre-established constraint relationships and objective functions between the operating parameters; wherein the objective function characterizes a function that determines the fault probability of a corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; solving the objective function based on the measured value and constraint relationships of the operating parameters to obtain the target estimated value of each operating parameter and its corresponding target fault probability; determining whether each target fault probability is less than the corresponding threshold; if not, confirming that the module corresponding to the target fault probability has a fault. Therefore, the above solution establishes a global fault diagnosis and determination method for the refrigeration system, transforming the problem of determining the fault of the refrigeration system's operating parameters into a problem of optimizing the operating parameter constraints; it considers the overall operating level of the refrigeration system, thereby avoiding fault diagnosis of individual devices in the refrigeration system, and is more suitable for practical engineering. By using digital analysis to locate faults in the refrigeration system, it is possible to achieve the goals of reducing the energy consumption of the refrigeration system, ensuring the performance and safety of the system, ensuring the temperature requirements of the production process, and improving the efficiency of equipment maintenance, measurement, fault finding and repair.

[0229] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0230] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0231] In this embodiment, a computer program is stored on a computer-readable storage medium. When the computer program is executed by a processor, it implements the steps described in the above method embodiment. The steps involve: acquiring measured values ​​of the operating parameters of each module in the refrigeration system; acquiring pre-established constraint relationships and objective functions between the operating parameters; wherein the objective function characterizes a function that determines the fault probability of a corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; solving the objective function based on the measured value and constraint relationships of the operating parameters to obtain the target estimated value of each operating parameter and its corresponding target fault probability; determining whether each target fault probability is less than the corresponding threshold; if not, confirming that the module corresponding to the target fault probability has a fault. Therefore, the above solution establishes a global fault diagnosis and determination method for the refrigeration system, transforming the problem of determining the fault of the operating parameters of the refrigeration system into a problem of optimizing the operating parameter constraints; considering the overall operating level of the refrigeration system, thus avoiding fault diagnosis of individual devices in the refrigeration system, making it more suitable for practical engineering. Locating refrigeration system faults through digital analysis can achieve the goals of reducing refrigeration system operating energy consumption, ensuring system operating performance and safety, ensuring the temperature requirements of production processes, and improving the efficiency of equipment maintenance measurement and fault finding and repair.

[0232] The foregoing has provided a detailed description of a method, apparatus, device, and medium for determining refrigeration system faults. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0233] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for determining faults in a refrigeration system, characterized in that, include: Obtain the measured values ​​of the operating parameters of each module in the refrigeration system; Obtain the pre-established constraint relationships and objective function among the operating parameters; wherein, the objective function characterizes a function that determines the failure probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; The objective function is solved based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimated values ​​of each operating parameter and its corresponding target failure probability. Determine whether the probability of each target failure is less than the corresponding threshold. If not, then it is confirmed that the module corresponding to the target failure probability is faulty; The process of establishing the objective function includes: The deviation threshold and the performance parameters of the measuring instrument for obtaining the operating parameters are described; wherein the deviation threshold characterizes the threshold at which a significant deviation occurs between the measured value and the estimated value of the operating parameters; and the performance parameters include at least an accuracy value. The objective function is established based on the deviation threshold, the performance parameters, the measured values ​​and the estimated values ​​of the operating parameters; The step of solving the objective function based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimates of each operating parameter and its corresponding target failure probability includes: An initial parent population is generated based on the measured values ​​of the operating parameters; wherein, individuals in the initial parent population represent the estimated values ​​of the operating parameters; Obtain the individual fitness and the objective function value corresponding to each individual in the initial parent population, and take the individual whose individual fitness in the initial parent population meets the first preset requirement as the current estimated value; Genetic operations are performed on the initial parent population to obtain the target offspring population; Obtain the individual fitness and the objective function value corresponding to each individual in the target offspring population, and take the individual fitness of the target offspring population that meets the second preset requirement as the new estimated value, so as to update the current estimated value through the new estimated value; Determine whether the preset number of iterations has been reached; If not, return to the step of performing genetic operations on the initial parent population to obtain the target offspring population; If so, the current estimated value is used as the target estimated value, and the objective function value is used as the target failure probability; Obtaining the individual fitness of the individual includes: A fitness function is constructed based on the constraints and the objective function; wherein the fitness function is a function that characterizes the degree to which the individual violates the constraints. The individual fitness of the individual is obtained according to the fitness function.

2. The method for determining refrigeration system faults according to claim 1, characterized in that, The process of establishing the constraint relationship between the operating parameters includes: Obtain the correlation between the various operating parameters; wherein, the correlation includes at least the mass conservation relationship and the energy conservation relationship; Establish the constraint relationships between the various operating parameters based on the aforementioned associations.

3. The method for determining refrigeration system faults according to claim 1, characterized in that, The genetic operations performed on the initial parent population to obtain the target offspring population include: The initial parent population is selected and replicated using a tournament method to obtain the initial offspring population. Gene recombination is performed on the initial offspring population through a linear combination of crossover operators to obtain the gene-recombined offspring population. The target offspring population is obtained by performing gene mutation operations on the offspring population after gene recombination through uniform mutation.

4. The method for determining refrigeration system faults according to any one of claims 1 to 3, characterized in that, After confirming that the module corresponding to the target failure probability has a failure, the method further includes: Output the fault location, fault cause, and fault-related location of the module; The operating parameters are corrected based on the target estimate corresponding to the module.

5. A refrigeration system fault determination device, characterized in that, include: The first acquisition module is used to acquire the measured values ​​of the operating parameters of each module in the refrigeration system; The second acquisition module is used to acquire the pre-established constraint relationship and objective function between the operating parameters; wherein, the objective function characterizes a function that determines the failure probability of the corresponding operating parameter based on the deviation between the measured value and the estimated value of the operating parameter; The processing module is used to solve the objective function based on the measured values ​​of the operating parameters and the constraint relationship to obtain the target estimated value of each operating parameter and its corresponding target failure probability; The judgment module is used to determine whether the failure probability of each target is less than the corresponding threshold; if not, the confirmation module is triggered. The confirmation module is used to confirm that the module corresponding to the target failure probability is faulty; The process of establishing the objective function includes: The deviation threshold and the performance parameters of the measuring instrument for obtaining the operating parameters are described; wherein the deviation threshold characterizes the threshold at which a significant deviation occurs between the measured value and the estimated value of the operating parameters; and the performance parameters include at least an accuracy value. The objective function is established based on the deviation threshold, the performance parameters, the measured values ​​and the estimated values ​​of the operating parameters; The step of solving the objective function based on the measured values ​​of the operating parameters and the constraint relationships to obtain the target estimates of each operating parameter and its corresponding target failure probability includes: An initial parent population is generated based on the measured values ​​of the operating parameters; wherein, individuals in the initial parent population represent the estimated values ​​of the operating parameters; Obtain the individual fitness and the objective function value corresponding to each individual in the initial parent population, and take the individual whose individual fitness in the initial parent population meets the first preset requirement as the current estimated value; Genetic operations are performed on the initial parent population to obtain the target offspring population; Obtain the individual fitness and the objective function value corresponding to each individual in the target offspring population, and take the individual fitness of the target offspring population that meets the second preset requirement as the new estimated value, so as to update the current estimated value through the new estimated value; Determine whether the preset number of iterations has been reached; If not, return to the step of performing genetic operations on the initial parent population to obtain the target offspring population; If so, the current estimated value is used as the target estimated value, and the objective function value is used as the target failure probability; Obtaining the individual fitness of the individual includes: A fitness function is constructed based on the constraints and the objective function; wherein the fitness function is a function that characterizes the degree to which the individual violates the constraints. The individual fitness of the individual is obtained according to the fitness function.

6. A refrigeration system fault determination device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the refrigeration system fault determination method as described in any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the refrigeration system fault determination method as described in any one of claims 1 to 4.

Images