Air conditioner fault detection method, system, electronic device and storage medium

Abstract

A method, system, electronic device and storage medium for fault detection of an air conditioner, relating to the technical field of fault detection of air conditioners. The method comprises: obtaining parameter values ​​corresponding to each dimension when the air conditioner is running, and determining the running state of the air conditioner based on the parameter values ​​corresponding to each dimension, wherein each dimension is at least one of pressure, temperature, current or rotation speed; when the running state is initially abnormal, determining the abnormal dimension and the fluctuation characteristics corresponding to each abnormal dimension based on the parameter values ​​corresponding to each dimension; performing fusion calculation on each fluctuation characteristic to obtain the fault probability value of the air conditioner; when the fault probability value is greater than the probability threshold, performing fault location based on each fluctuation characteristic to obtain the fault detection result of the air conditioner. The implementation of the technical solution provided by the present application improves the accuracy of air conditioner fault detection.

Description

Technical Field

[0001] The present application relates to the technical field of air conditioner fault detection, and in particular to an air conditioner fault detection method, system, electronic device and storage medium. Background Art

[0002] With the improvement of people's living standards, air conditioners have become an indispensable electrical appliance. As a complex refrigeration cycle system, the operating state of the air conditioning system is affected by multiple physical parameters, including but not limited to pressure, temperature, current, speed, etc. In the actual operation process, the air conditioner may have various faults. Timely detection and diagnosis of these faults is of great significance to ensure the normal operation and service life of the air conditioner.

[0003] At present, air conditioner fault detection is mainly based on a single parameter threshold judgment detection method, which determines whether the system has a fault by detecting whether a certain parameter exceeds the preset threshold. However, since the normal fluctuation range of each parameter will change under different operating environments and working conditions of the air conditioner, it is easy to make a misjudgment by relying solely on the comparison of a single parameter with a fixed threshold, resulting in low accuracy of air conditioner fault detection. Summary of the invention

[0004] The present application provides a method, system, electronic device and storage medium for detecting faults of an air conditioner, which improve the accuracy of detecting faults of the air conditioner.

[0005] In a first aspect, the present application provides a method for detecting a fault of an air conditioner, the method comprising:

[0006] Acquire parameter values ​​corresponding to each dimension when the air conditioner is running, and determine the running state of the air conditioner based on the parameter values ​​corresponding to each dimension;

[0007] When the operating state is initially abnormal, determining the abnormal dimension and the fluctuation characteristics corresponding to each abnormal dimension based on the parameter values ​​corresponding to each dimension;

[0008] Performing fusion calculation on each of the fluctuation characteristics to obtain a failure probability value of the air conditioner;

[0009] When the fault probability value is greater than a probability threshold, fault location is performed based on each of the fluctuation characteristics to obtain a fault detection result of the air conditioner.

[0010] By adopting the above technical solution, the operation of the air conditioner can be comprehensively monitored by obtaining the parameter values ​​corresponding to each dimension when the air conditioner is running and determining the operating status; when the operating status is initially abnormal, the abnormal dimension and its fluctuation characteristics are further determined, avoiding the misjudgment that may be caused by relying solely on the comparison of a single parameter with a fixed threshold; the fault probability value is obtained by fusing and calculating the fluctuation characteristics of each abnormal dimension, fully considering the fluctuation changes of parameters under different operating environments and working conditions; when the fault probability value exceeds the probability threshold, the fault is located based on the fluctuation characteristics, thereby achieving accurate fault detection and improving the accuracy of air conditioner fault detection.

[0011] In a second aspect of the present application, a fault detection system for an air conditioner is provided, the system comprising:

[0012] An operating state determination module, used to obtain parameter values ​​corresponding to various dimensions when the air conditioner is running, and determine the operating state of the air conditioner based on the parameter values ​​corresponding to each dimension, wherein each dimension is at least one of pressure, temperature, current or rotation speed;

[0013] A fluctuation characteristic determination module, used for determining the abnormal dimension and the fluctuation characteristic corresponding to each abnormal dimension based on the parameter value corresponding to each dimension when the operating state is initially abnormal;

[0014] A probability value calculation module, used for performing fusion calculation on each of the fluctuation characteristics to obtain a failure probability value of the air conditioner;

[0015] The detection result generating module is used to locate the fault based on each of the fluctuation characteristics when the fault probability value is greater than the probability threshold, so as to obtain the fault detection result of the air conditioner.

[0016] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0017] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0018] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0019] The present application can comprehensively monitor the operation of the air conditioner by obtaining the parameter values ​​corresponding to each dimension when the air conditioner is running and determining the operating status; when the operating status is initially abnormal, the abnormal dimension and its fluctuation characteristics are further determined to avoid the misjudgment that may be caused by relying solely on the comparison of a single parameter with a fixed threshold; the fault probability value is obtained by fusing and calculating the fluctuation characteristics of each abnormal dimension, fully considering the fluctuation changes of parameters under different operating environments and working conditions; when the fault probability value exceeds the probability threshold, the fault is located based on the fluctuation characteristics, thereby achieving accurate fault detection and improving the accuracy of air conditioner fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a method for detecting a fault of an air conditioner provided in an embodiment of the present application;

[0021] Figure 2 It is a module schematic diagram of a fault detection system for an air conditioner provided in an embodiment of the present application;

[0022] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0023] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0024] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0025] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of 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 "for example" or "for example" is intended to present related concepts in a specific way.

[0026] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0027] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0028] Please refer to Figure 1 , a flowchart of a method for fault detection of an air conditioner is proposed, the method can be implemented by a computer program, can be implemented by a single-chip microcomputer, and can also be run on an air conditioner fault detection system, the computer program can be integrated in a computer device, and can also be run as an independent tool application, specifically, the method includes steps 10 to 40, the above steps are as follows:

[0029] Step 10: Obtain parameter values ​​corresponding to each dimension when the air conditioner is running, and determine the running state of the air conditioner based on the parameter values ​​corresponding to each dimension, where each dimension is at least one of pressure, temperature, current or speed.

[0030] The embodiments of the present application can be applied to large-scale commercial central air-conditioning systems, especially in commercial complexes, industrial plants, data centers, etc. The air-conditioning systems in such scenarios usually have the following characteristics: large equipment scale, high system complexity, multiple operating parameters, strict control accuracy requirements, wide range of fault impact, and high maintenance cost.

[0031] The parameters corresponding to each dimension in the embodiment of the present application refer to physical quantities reflecting the operating status of the air conditioning system, including pressure, temperature, current, speed, etc. Among them, the pressure parameter value includes the compressor suction pressure and exhaust pressure, the temperature parameter value may include the condenser temperature, the evaporator temperature, and the indoor ambient temperature, the current parameter value includes the compressor operating current, and the speed parameter includes the compressor speed, the fan speed, etc.

[0032] In the embodiment of the present application, the operating state of the air conditioner refers to the working condition of the air conditioner system at a certain moment, including normal operating state and preliminary abnormal state. The normal operating state indicates that the changes of the parameters of each dimension are within a reasonable range; the preliminary abnormal state indicates that the changes of the parameters of the dimension are beyond the reasonable range, and there may be hidden dangers of failure.

[0033] Specifically, the parameter values ​​corresponding to each dimension, such as compressor suction pressure, exhaust pressure, condenser temperature, evaporator temperature, indoor ambient temperature, compressor operating current, compressor speed, and fan speed, are collected in real time through various sensors in the air-conditioning system. Since there is a physical correlation between the parameters in the air-conditioning system, in actual operation, when a parameter is abnormal, it often causes a chain change in the parameters of its adjacent dimensions. Therefore, the parameter change rate of the corresponding parameter value of each dimension within a preset time period (for example, 10 minutes) is obtained, and the ratio between the parameter change rate of each dimension and the parameter change rate of the adjacent dimension is determined. For example, the ratio of the change rate of the compressor suction pressure to the change rate of the exhaust pressure is calculated, and the ratio of the change rate of the condenser temperature to the change rate of the compressor current is calculated. When any ratio exceeds the corresponding standard range (for example, the compressor suction and exhaust pressure ratio exceeds the normal range of 1.2-1.5), the operating state of the air conditioner is determined to be initially abnormal. In this way, not only the change of a single parameter is considered, but more importantly, the change relationship between the parameters of adjacent dimensions is examined, which effectively avoids misjudgment caused by changes in working conditions and lays the foundation for subsequent fault detection.

[0034] Based on the above embodiment, as an optional embodiment, the step of determining the operating state of the air conditioner based on the parameter values ​​corresponding to each dimension may further include the following steps:

[0035] Step 101: Obtain the parameter change rate of the parameter value corresponding to each dimension within a preset time period.

[0036] Specifically, during the operation of a large commercial central air-conditioning system, the instantaneous value of a single parameter may fluctuate greatly due to factors such as load changes and ambient temperature fluctuations. Therefore, this embodiment first obtains multiple sets of sampling values ​​of each dimension within a preset time period (for example, 10 minutes), and for each dimension parameter, calculates its rate of change within the time period. Taking the compressor suction pressure as an example, the parameter change rate is obtained by calculating (current sampling value-initial sampling value) / initial sampling value; similarly, the parameter change rates of other dimensions such as compressor exhaust pressure, condenser temperature, and evaporator temperature are calculated.

[0037] Step 102: Determine the ratio between the parameter change rate of each dimension and the parameter change rate of the adjacent dimension.

[0038] Specifically, due to the physical coupling relationship between the components in the refrigeration cycle system, the changes in the parameters of adjacent dimensions under normal working conditions should show a certain correlation. For example, when the suction pressure of the compressor rises, the exhaust pressure will usually rise accordingly, and the ratio of the change rates of the two should be maintained within a reasonable range. Based on this principle, the ratio of the parameter change rates between adjacent dimensions with physical associations is calculated, such as the ratio of the compressor suction and exhaust pressure change rates, the ratio of the condenser temperature to the compressor current change rate, etc.

[0039] Step 103: When any ratio exceeds the corresponding standard range, it is determined that the operating state of the air conditioner is initially abnormal.

[0040] Specifically, when any ratio exceeds its corresponding standard range (for example, the ratio of the change rate of the suction and exhaust pressures exceeds the normal range of 0.8-1.2, or the ratio of the change rate of the condenser temperature to the compressor current exceeds the preset range), the system is judged to be in a preliminary abnormal state. By introducing the parameter change rate analysis of the time dimension and examining the correlation between the changes in adjacent dimensions, the influence of normal operating condition fluctuations can be effectively filtered out, and the reliability of abnormal state judgment can be improved.

[0041] Step 20: When the operating state is initially abnormal, determine the abnormal dimension and the fluctuation characteristics corresponding to each abnormal dimension based on the parameter value corresponding to each dimension.

[0042] In the embodiment of the present application, an abnormal dimension refers to a dimension parameter whose parameter change rate ratio to the adjacent dimension parameter change rate exceeds the standard range. For example, when the ratio of the change rate of the compressor suction pressure to the exhaust pressure exceeds the standard range of 0.8-1.2, the compressor suction pressure and the exhaust pressure are both determined as abnormal dimensions; when the ratio of the change rate of the condenser temperature to the compressor current exceeds the preset range, the condenser temperature and the compressor current are both determined as abnormal dimensions.

[0043] In the embodiment of the present application, the fluctuation characteristics corresponding to the abnormal dimension refer to multiple characteristic values ​​used to quantitatively describe the parameter changes of the abnormal dimension within a preset time period, including but not limited to the fluctuation amplitude, fluctuation frequency and fluctuation slope.

[0044] Specifically, when the operating state of the air-conditioning system is determined to be initially abnormal, it is necessary to further locate the specific abnormal dimension and analyze its abnormal degree. First, for each dimensional parameter, calculate the ratio of its change rate to the adjacent dimensional parameter. Taking the compressor as an example, calculate the ratio of the change rate of the suction pressure to the exhaust pressure, the ratio of the change rate of the exhaust pressure to the condenser temperature, etc. When a certain ratio exceeds the corresponding standard range (for example, the ratio of the change rate of the suction and exhaust pressure exceeds the range of 0.8-1.2), the two dimensions corresponding to the ratio are determined as abnormal dimensions. After determining the abnormal dimension, for each abnormal dimension, multiple groups of parameter values ​​are collected within a preset time period (for example, once per second for 10 minutes), and their fluctuation characteristics are calculated. The fluctuation amplitude can be obtained by calculating (maximum sampling value-minimum sampling value) / average value, which is used to characterize the severity of parameter changes; the fluctuation frequency is obtained by calculating the number of times the parameter value exceeds the mean line divided by the length of the preset time period, which is used to characterize the speed of parameter changes; the fluctuation slope is obtained by calculating the parameter difference between adjacent sampling moments and dividing it by the sampling time interval, which is used to characterize the trend characteristics of parameter changes. For example, for abnormal compressor suction pressure, characteristic values ​​such as fluctuation amplitude of 25%, fluctuation frequency of 0.2Hz, and fluctuation slope of 0.5MPa / min may be obtained. In this way, not only can the abnormal dimension be accurately identified, but also the change characteristics of the abnormal dimension can be quantitatively described, providing an important basis for subsequent fault diagnosis.

[0045] Based on the above embodiment, as an optional embodiment, the step of determining the abnormal dimension and the fluctuation feature corresponding to each abnormal dimension based on the parameter value corresponding to each dimension may further include the following steps:

[0046] Step 201: Determine the time series data of the parameter values ​​corresponding to each dimension.

[0047] Specifically, in order to accurately analyze the dynamic change characteristics of various dimensional parameters of the air-conditioning system, the data acquisition module in the air-conditioning control system is first used to continuously sample various dimensional parameters such as compressor suction pressure, exhaust pressure, condenser temperature, evaporator temperature, etc. according to a preset sampling period (for example, 1 second) to obtain time series data within a preset time period (for example, 10 minutes).

[0048] Step 202: Calculate the fluctuation amplitude, fluctuation frequency and fluctuation slope corresponding to each dimension based on the time series data of each dimension, where the fluctuation amplitude is the maximum deviation of the parameter value, the fluctuation frequency is the number of fluctuations of the parameter value per unit time, and the fluctuation slope is the average rate of change of the parameter value.

[0049] Specifically, based on the acquired time series data, the fluctuation characteristic values ​​corresponding to each dimension are calculated respectively. In the embodiment of the present application, the fluctuation characteristics include fluctuation amplitude, fluctuation frequency and fluctuation slope. For the calculation of the fluctuation amplitude, the average value of the parameter value in the preset time period is first determined, and then the absolute value of the difference between each sample value and the average value is calculated, and the maximum difference is determined as the fluctuation amplitude of the dimension, which characterizes the degree to which the parameter deviates from the normal value. For example, the average value of the suction pressure of a compressor is 2MPa, and the maximum deviation is 0.5MPa, then its fluctuation amplitude is 0.5MPa.

[0050] The fluctuation frequency is calculated by counting the number of times the parameter value crosses the average value within a preset time period and dividing it by the length of the preset time period. For example, if the compressor suction pressure crosses the average value 120 times within 10 minutes, its fluctuation frequency is 0.2 Hz.

[0051] For the calculation of the fluctuation slope, the ratio of the parameter change of all adjacent sampling points within the preset time period to the sampling time interval is calculated, and the average value is taken as the fluctuation slope to characterize the overall change trend of the parameter. For example, if the average change rate of the compressor suction pressure within 10 minutes is 0.5MPa / min, then its fluctuation slope is 0.5MPa / min. The fluctuation characteristic values ​​obtained in this way can fully reflect the changes in parameters of each dimension and provide a reliable data basis for subsequent abnormal state identification.

[0052] Step 203: Determine any dimension whose fluctuation amplitude exceeds the first threshold, whose fluctuation frequency exceeds the second threshold, or whose fluctuation slope exceeds the third threshold as an abnormal dimension, and use the fluctuation amplitude, fluctuation frequency and fluctuation slope of the abnormal dimension as fluctuation features.

[0053] Specifically, the fluctuation characteristic values ​​of each dimension are compared with preset thresholds. These thresholds are normal operating reference values ​​obtained based on statistical analysis of a large amount of historical operating data, wherein the first threshold is used to limit the normal range of the fluctuation amplitude, the second threshold is used to limit the normal range of the fluctuation frequency, and the third threshold is used to limit the normal range of the fluctuation slope. In specific implementation, the fluctuation characteristic values ​​of the parameters of each dimension are first obtained, and then compared with the corresponding thresholds. Taking the compressor suction pressure as an example, if its fluctuation amplitude is 0.5MPa, which exceeds the first threshold of 0.3MPa; or the fluctuation frequency is 0.2Hz, which exceeds the second threshold of 0.15Hz; or the fluctuation slope is 0.5MPa / min, which exceeds the third threshold of 0.4MPa / min, the compressor suction pressure is determined as an abnormal dimension. For the parameters determined as abnormal dimensions, their fluctuation amplitude, fluctuation frequency and fluctuation slope are used as the fluctuation characteristics of the abnormal dimension to characterize its degree of abnormality. For example, if the compressor suction pressure is determined to be an abnormal dimension, its fluctuation characteristics are: fluctuation amplitude 0.5MPa, fluctuation frequency 0.2Hz, and fluctuation slope 0.5MPa / min. This multi-dimensional threshold judgment method can comprehensively consider all aspects of parameter changes, capture sudden large fluctuations (through fluctuation amplitude), discover high-frequency small-amplitude abnormal fluctuations (through fluctuation frequency), and identify slow but continuous abnormal changes (through fluctuation slope), thereby improving the accuracy and reliability of abnormal dimension identification.

[0054] Step 30: Perform fusion calculation on each fluctuation feature to obtain the failure probability value of the air conditioner.

[0055] Specifically, in order to accurately evaluate the overall fault state of the air-conditioning system, this embodiment adopts a multi-level feature fusion calculation method. First, for each abnormal dimension, the ratio of its fluctuation characteristic value to the corresponding threshold is calculated, that is, the ratio of the fluctuation amplitude to the first threshold, the ratio of the fluctuation frequency to the second threshold, and the ratio of the fluctuation slope to the third threshold. Then, based on these ratios, the single-dimensional fault probability value is calculated, and then, considering the mutual influence between the parameters of each dimension in the air-conditioning system, the coupling coefficient between any two abnormal dimensions is calculated according to the single-dimensional fault probability value. Based on the calculated coupling coefficient, a coupling matrix is ​​further constructed, and each element in the matrix reflects the coupling strength between the corresponding two dimensions. Finally, by extracting features from the coupling matrix, a comprehensive eigenvalue is obtained, which contains both the absolute size information of each element and the relative difference between the elements. Finally, the fault probability value of the air conditioner is calculated based on the comprehensive eigenvalue. Through this multi-level feature fusion method, not only the abnormality of a single dimension is considered, but also the correlation information between dimensions is fully utilized, so that the final fault probability value can fully reflect the health status of the air-conditioning system, and provide a reliable quantitative basis for fault diagnosis and maintenance decisions.

[0056] Based on the above embodiment, as another optional embodiment, the step of fusing and calculating the fluctuation characteristics to obtain the failure probability value of the air conditioner may further include the following steps:

[0057] Step 301: For any abnormal dimension, calculate a first ratio of the fluctuation amplitude to the first threshold, a second ratio of the fluctuation frequency to the second threshold, and a third ratio of the fluctuation slope to the third threshold.

[0058] Specifically, in order to convert the fluctuation characteristics of different dimensions and numerical ranges into comparable dimensionless parameters, it is necessary to standardize the fluctuation characteristics of each abnormal dimension. In the specific implementation, first obtain the fluctuation amplitude, fluctuation frequency and fluctuation slope of the abnormal dimension, as well as the corresponding threshold. Taking the compressor suction pressure as an example, if its fluctuation amplitude is 0.5MPa and the first threshold is 0.3MPa, the first ratio of 1.67 is obtained by dividing the two, which reflects the degree to which the fluctuation amplitude exceeds the normal range; if its fluctuation frequency is 0.2Hz and the second threshold is 0.15Hz, the second ratio of 1.33 is obtained by division, which characterizes the severity of the abnormal fluctuation frequency; if its fluctuation slope is 0.5MPa / min and the third threshold is 0.4MPa / min, the third ratio of 1.25 is obtained by division, which reflects the abnormal degree of the parameter change rate. The same calculation method is also applicable to other abnormal dimensions, such as exhaust pressure, condenser temperature, etc. By calculating these ratios, the fluctuation characteristics of different physical quantities are uniformly converted into the degree of deviation relative to their respective thresholds, making different dimensions and different characteristics comparable, laying the foundation for subsequent fault probability calculations. This standardized processing method not only solves the problem of inconsistent dimensions between different physical quantities, but also highlights the degree of abnormality and improves the accuracy of fault diagnosis.

[0059] Step 302: Substitute the first ratio, the second ratio, and the third ratio into the first calculation formula to obtain the single-dimensional failure probability value corresponding to each abnormal dimension.

[0060] Specifically, the first ratio, the second ratio, and the third ratio are substituted into the first calculation formula to obtain the single-dimensional failure probability value corresponding to each abnormal dimension. The first calculation formula is: , where P i is the single-dimensional failure probability value of the i-th abnormal dimension, A i is the first ratio, F i is the second ratio, T i is the third ratio, α, β, and γ are respectively the preset weight coefficients, .

[0061] In the first formula, the first ratio A is processed by the hyperbolic tangent function tanh i , because the hyperbolic tangent function can map the input value to between -1 and 1, it provides a smooth and bounded way to represent the impact of fluctuation amplitude exceeding the threshold. This mapping can emphasize the abnormality of the amplitude while avoiding excessive contribution to the probability of failure. The second ratio F is processed by the cosine function cos i The cosine function provides periodic modulation, reflecting the impact of periodic frequency changes on system stability. Multiplying by π / 2 is to adjust the impact range of periodicity to adapt it to actual application scenarios. The third ratio T is processed by the Sigmoid function. i , the Sigmoid function can map any real number to between 0 and 1, providing a smooth conversion method for dealing with fluctuating slopes. The cubic term strengthens the impact of slope changes on the probability of failure, so that subtle slope changes are reasonably amplified in fault prediction. By integrating these calculation results, we can not only evaluate the impact of each abnormal dimension separately, but also combine their interactive effects to more accurately predict the overall failure risk of the system.

[0062] For example, in the embodiment of the present application, the weight coefficients α=0.5, β=1.0, and γ=0.2 are set. Assume that in a certain dimension, the calculated first ratio A i =1.5, the second ratio F i =0.8, the third ratio T i =2.0, then the single-dimension failure probability value of this dimension is: .

[0063] Step 303: Calculate the failure probability value of the air conditioner based on the failure probability values ​​of each single dimension.

[0064] Specifically, in the air-conditioning system, there is often a complex mutual influence relationship between the abnormal dimensions. In order to accurately reflect this correlation, this embodiment designs a multi-dimensional fault assessment method based on a coupling matrix. First, the degree of correlation between any two abnormal dimensions is quantified by calculating the coupling coefficient. The calculation of the coupling coefficient comprehensively considers three key factors: fault probability difference, timing relationship, and probability product effect, so as to calculate the coupling coefficient between the dimensions, and then construct a coupling matrix based on the coupling coefficient. Each element of the coupling matrix can fully reflect the correlation characteristics between the corresponding dimension pairs. Finally, the fault probability value of the air conditioner is calculated based on the coupling matrix.

[0065] Based on the above embodiment, as another optional embodiment, the step of calculating the failure probability value of the air conditioner based on each single-dimensional failure probability value may further include the following steps:

[0066] Step 3031: Substitute each single-dimensional fault probability value into the second calculation formula to obtain the coupling coefficient between each dimension.

[0067] Specifically, the calculation of the coupling coefficient aims to quantify the strength of the mutual influence between two dimensions. In a multi-dimensional system, an abnormality in one dimension may affect or be affected by the state of another dimension. By calculating this coupling relationship, the overall behavior of the system can be predicted more accurately, especially when complex failure modes occur. i and P j To estimate the coupling coefficient R between different anomaly dimensions in the air conditioning system ij , substitute the fault probability value of each single dimension into the second calculation formula to obtain the coupling coefficient between each dimension. The second calculation formula is: , where R ij is the coupling coefficient of the quality inspection of the i-th and j-th abnormal dimensions, t i and t j are the anomaly occurrence moments of the i-th anomaly dimension and the j-th anomaly dimension, respectively. is the time constant.

[0068] In the second formula, It partially reflects the probability difference between the two dimensions. The larger the difference, the more significant the mutual influence between the two dimensions may be. Some suggest that if the anomalies in two dimensions occur longer apart, the impact between them will gradually weaken. It provides a smooth and bounded way to express the product of two fault probability values, reflecting the strength of their interaction. By combining these elements in a logarithmic function, the coupling coefficient is able to comprehensively consider the compound effects of probability difference, time difference and interaction. The logarithmic function further ensures the smoothness and nonlinear expansion of the result, making it more suitable for describing the dynamic characteristics of complex systems.

[0069] For example, assuming that the single-dimensional failure probability values ​​of the two abnormal dimensions are P i = 0.7 and P j =0.4, abnormal time t i = 5 seconds and t j =10 seconds, time constant τ=20 seconds. .

[0070] Step 3032: Substitute each coupling coefficient into the third calculation formula to obtain each element value in the coupling matrix.

[0071] Specifically, the purpose of constructing the coupling matrix is ​​to form a comprehensive representation that describes the strength and characteristics of the mutual influence between the various fault dimensions in the system. In complex systems, the impact of a single fault dimension is often closely related to the state of other dimensions. Therefore, the coupling matrix can more accurately predict system behavior and provide data support for fault prevention and maintenance decisions. Substitute each coupling coefficient into the third calculation formula to obtain the value of each element in the coupling matrix. The third calculation formula is: , where M ij is the element value of the i-th row and j-th column in the coupling matrix, P i is the single-dimensional failure probability value of the i-th abnormal dimension, P j is the single-dimension failure probability value of the j-th abnormal dimension.

[0072] In the third calculation formula, R ij Reflecting the direct interaction strength between the two dimensions, sinh(P i +P j ) is used to emphasize the effect of adding two fault probability values. This nonlinear function can effectively amplify larger fault probability values ​​and have a greater impact on the overall stability of the system. The difference between the two failure probability values ​​is further processed in a way that emphasizes that even small probability differences can lead to significant changes in system behavior. This calculation not only takes into account the interaction between the two dimensions, but also effectively amplifies the impact of these interactions through the use of nonlinear and exponential functions.

[0073] Step 3033: Calculate the failure probability value of the air conditioner based on the coupling matrix.

[0074] Specifically, the values ​​of each element in the coupling matrix are substituted into the fourth calculation formula to obtain the comprehensive eigenvalue,

[0075] The fourth calculation formula is: , where S is the comprehensive eigenvalue. This comprehensive eigenvalue is intended to provide a quantitative measure that reflects the total impact of the comprehensive interaction between all abnormal dimensions in the system. By calculating this value, the overall failure risk of the system can be more comprehensively assessed, thereby providing key information for maintenance and failure prevention. In the fourth calculation formula, M ij is the element value of the i-th row and j-th column in the coupling matrix, To adjust M ij The impact of M ij When is larger, its influence is nonlinearly enhanced. is the sum of the absolute values ​​of all elements in the coupling matrix and is used as a normalization factor. This ensures that S is comparable between different systems or coupling matrices of different sizes. This calculation method provides a comprehensive indicator that reflects the overall impact of the complex interactions between all possible fault dimensions in the system. This indicator can quickly determine the health of the system and predict potential large-scale failures.

[0076] Substituting the comprehensive characteristic value into the fifth calculation formula, the failure probability value of the air conditioner is obtained. The fifth calculation formula is: , where P is the failure probability value of the air conditioner and K is the preset adjustment coefficient. By calculating the failure probability value, the previously calculated comprehensive characteristic value can be converted into an actual probability metric, which represents the current failure risk of the system. This probability value provides a clear indicator for maintenance decisions, helping to determine the maintenance priority and necessary maintenance time window of the system. In the fifth calculation formula, K is the preset adjustment coefficient, which is used to adjust the degree of influence of the comprehensive characteristic value S on the result, is an exponential decay function used to convert the comprehensive characteristic value into a value between 0 and 1, reflecting the basic part of the failure probability. is a hyperbolic tangent function that provides an adjustment to the base probability to take into account the nonlinear effect of the size of the comprehensive eigenvalue on the probability. This calculation method can effectively convert the comprehensive eigenvalue into a practical failure probability indicator that not only takes into account the interaction of abnormal dimensions in the system, but also adjusts the overall impact of these interactions through nonlinear functions.

[0077] Step 40: When the fault probability value is greater than the probability threshold, the fault location is performed based on each fluctuation feature to obtain a fault detection result of the air conditioner.

[0078] Specifically, when the fault probability value of the air-conditioning system exceeds the preset probability threshold, it is necessary to further analyze the fluctuation characteristics of each abnormal dimension to accurately locate the specific type and location of the fault. This embodiment adopts a fault location method based on fluctuation feature pattern matching, and identifies the specific fault type by analyzing the combined characteristics of fluctuation amplitude, fluctuation frequency and fluctuation slope. First, a fault feature library is established, which contains fluctuation feature patterns corresponding to various typical faults. For example, a refrigerant leakage fault is usually manifested as a slow decrease in the suction pressure of the compressor (smaller fluctuation amplitude and fluctuation frequency, negative fluctuation slope), while a compressor valve fault is manifested as a rapid fluctuation of the suction pressure (larger fluctuation amplitude and fluctuation frequency, and the fluctuation slope is alternating between positive and negative). Based on these preset feature patterns, the currently detected abnormality can be pattern matched. In addition, this embodiment also considers the influence of the correlation between abnormal dimensions on fault location. By analyzing the coupling relationship of each abnormal dimension in the aforementioned coupling matrix, the accuracy of fault location can be further verified. For example, if the abnormality of the compressor suction and exhaust pressure has a strong coupling relationship, and the temporal relationship of the fluctuation characteristics conforms to the propagation law of the valve fault, the reliability of the fault location result is further confirmed.

[0079] Based on the above embodiment, as another optional embodiment, when the fault probability value is greater than the probability threshold, the step of locating the fault based on each fluctuation feature to obtain the fault detection result of the air conditioner may further include the following steps:

[0080] Step 401: when the fault probability value is greater than the probability threshold, a preset fault feature library is obtained, where the fault feature library includes multiple fault types and multiple groups of historical fluctuation features corresponding to each fault type.

[0081] Specifically, in order to achieve accurate diagnosis of air conditioner faults, this embodiment designs a matching method based on a fault feature library. The fault feature library is a knowledge base built through a large amount of historical operation data and expert experience summary, which includes a variety of typical fault types such as refrigerant leakage, compressor valve failure, and heat exchanger frost. Each fault type corresponds to multiple groups of historical fluctuation feature data, which record in detail the characteristic combination of the fluctuation amplitude, fluctuation frequency, and fluctuation slope of each dimensional parameter when the fault occurs.

[0082] Step 402: Match the fluctuation characteristics of each abnormal dimension with the fault feature library to obtain a preliminary fault type.

[0083] Specifically, when the system detects that the fault probability value exceeds the preset probability threshold (for example, 0.8), the preset fault feature library is first called. Taking the compressor valve fault as an example, its feature library contains multiple sets of historical data. For example, in a certain fault record, the fluctuation amplitude of the suction pressure is 0.45-0.55MPa, the fluctuation frequency is 0.18-0.22Hz, and the fluctuation slope is -0.35 to -0.25MPa / min. At the same time, the exhaust pressure fluctuates abnormally, with a fluctuation amplitude of 0.75-0.85MPa, a fluctuation frequency of 0.23-0.27Hz, and a fluctuation slope of 0.35-0.45MPa / min. The fluctuation features of each abnormal dimension currently obtained are matched and analyzed with the historical data in the fault feature library. The matching process uses a similarity calculation method to calculate the Euclidean distance or cosine similarity between the current fluctuation feature and the historical features of each fault type in the feature library. For example, when the fluctuation amplitude of the compressor suction pressure is detected to be 0.5MPa, the fluctuation frequency is 0.2Hz, and the fluctuation slope is -0.3MPa / min, the system will calculate the matching degree between this set of characteristic values ​​and the historical characteristics of each fault type in the feature library. Through the matching analysis of the fluctuation characteristics, the system can find the fault type that is most similar to the current abnormality. For example, if the currently detected fluctuation characteristics have the highest similarity with the historical characteristics of the compressor valve fault, it is preliminarily determined that the current fault type is a compressor valve fault. Since the feature library contains multiple sets of historical data, it can cover the characteristic changes of the same fault type under different working conditions, thereby improving the adaptability of diagnosis; secondly, through the comprehensive matching of the fluctuation characteristics of multiple abnormal dimensions, the misjudgment caused by the fluctuation of a single parameter can be effectively avoided; finally, the feature library can be continuously updated and expanded, and with the accumulation of operating data, the accuracy of diagnosis will continue to improve.

[0084] Step 403: A dimension association model is established based on a preset air-conditioning operation mechanism. The dimension association model is a physical coupling relationship and constraint conditions between dimensions.

[0085] Specifically, in order to further improve the accuracy and reliability of fault diagnosis, this embodiment introduces a dimensional association verification method based on the air conditioning operation mechanism on the basis of feature matching. The dimensional association model is established based on the thermodynamic principles and engineering experience of the air conditioning system. The model describes in detail the physical coupling relationship and constraints between the parameters of each dimension of the system, such as the thermodynamic relationship between the compressor suction and exhaust pressure, condenser temperature, evaporator temperature and other parameters, and the energy balance relationship between the parameters such as refrigerant flow and compressor power. Taking the compressor valve failure as an example, the dimensional association model defines the constraints that the parameters of each dimension should meet when the failure occurs. For example, when the suction valve fails, according to the working principle of the compressor, the fluctuations of the suction pressure and the exhaust pressure should have a significant phase difference, and the fluctuation frequency should be associated with the operating frequency of the compressor; at the same time, due to the obstruction of the suction process, the refrigerant flow rate will decrease, which will affect the cooling capacity of the evaporator and increase the evaporator temperature. These parameter changes need to comply with the constraints of the laws of thermodynamics.

[0086] Step 404: verify and supplement the preliminary fault type according to the dimensional association model to obtain the target fault type, and generate a fault detection result including the target fault type.

[0087] Specifically, after the preliminary fault type is obtained through matching the fault feature library, the dimensional association model can be used for verification. Taking the compressor valve fault as an example, assuming that the compressor suction pressure is currently detected to be 0.5MPa, the exhaust pressure is 2.2MPa, and the evaporator temperature is 8°C, although the fluctuation characteristics of these parameters match the feature library of the valve fault, they still need to be verified by the dimensional association model for rationality. The system will check whether these parameters meet the preset physical constraints, such as whether the suction and exhaust pressure ratio is within a reasonable range, whether the pressure fluctuation and temperature change conform to the thermodynamic law, etc. Through dimensional association verification, possible abnormal combinations can be identified. For example, if it is found that in addition to the typical characteristics of the compressor valve fault, the condenser temperature is abnormally high and does not conform to the thermodynamic constraints, this may indicate that there is a condenser fan fault at the same time. This physical model-based verification can not only confirm the reliability of the preliminary diagnosis results, but also discover potential associated faults, thereby obtaining a more complete target fault type. Finally, the system integrates the verified target fault type together with the key diagnostic basis into the fault detection result. This result not only includes the type of fault determination, but also includes key parameter information supporting the determination, such as fluctuation characteristic data of abnormal dimensions, correlation analysis results between parameters, etc.

[0088] See also Figure 2 , is a module schematic diagram of an air conditioner fault detection system provided in an embodiment of the present application, wherein the system includes:

[0089] An operating state determination module, used to obtain parameter values ​​corresponding to various dimensions when the air conditioner is running, and determine the operating state of the air conditioner based on the parameter values ​​corresponding to each dimension, wherein each dimension is at least one of pressure, temperature, current or rotation speed;

[0090] A fluctuation characteristic determination module, used for determining the abnormal dimension and the fluctuation characteristic corresponding to each abnormal dimension based on the parameter value corresponding to each dimension when the operating state is initially abnormal;

[0091] A probability value calculation module, used for performing fusion calculation on each of the fluctuation characteristics to obtain a failure probability value of the air conditioner;

[0092] The detection result generating module is used to locate the fault based on each of the fluctuation characteristics when the fault probability value is greater than the probability threshold, so as to obtain the fault detection result of the air conditioner.

[0093] Optionally, the operating state determination module is further used to obtain the parameter change rate of the parameter value corresponding to each dimension within a preset time period;

[0094] Determine the ratio between the parameter change rate of each dimension and the parameter change rate of an adjacent dimension;

[0095] When any of the ratios exceeds the corresponding standard range, it is determined that the operating state of the air conditioner is initially abnormal.

[0096] Optionally, the fluctuation feature determination module is further used to determine the time series data of the parameter value corresponding to each dimension;

[0097] Calculate the fluctuation amplitude, fluctuation frequency and fluctuation slope corresponding to each dimension according to the time series data of each dimension, wherein the fluctuation amplitude is the maximum deviation of the parameter value, the fluctuation frequency is the number of fluctuations of the parameter value per unit time, and the fluctuation slope is the average rate of change of the parameter value;

[0098] A dimension whose fluctuation amplitude exceeds the first threshold, whose fluctuation frequency exceeds the second threshold, or whose fluctuation slope exceeds the third threshold is determined as an abnormal dimension, and the fluctuation amplitude, fluctuation frequency and fluctuation slope of the abnormal dimension are used as fluctuation features.

[0099] Optionally, the probability value calculation module is further used to calculate, for any of the abnormal dimensions, a first ratio of the fluctuation amplitude to the first threshold, a second ratio of the fluctuation frequency to the second threshold, and a third ratio of the fluctuation slope to the third threshold;

[0100] Substituting the first ratio, the second ratio and the third ratio into a first calculation formula to obtain a single-dimensional failure probability value corresponding to each of the abnormal dimensions;

[0101] Calculating a failure probability value of the air conditioner based on each of the single-dimensional failure probability values;

[0102] The first calculation formula is: , where P i is the single-dimensional failure probability value of the i-th abnormal dimension, A i is the first ratio, F i is the second ratio, T i is the third ratio, α, β, and γ are respectively the preset weight coefficients, .

[0103] Optionally, the probability value calculation module is further used to substitute each single-dimensional fault probability value into a second calculation formula to obtain a coupling coefficient between each dimension;

[0104] The second calculation formula is: , where R ij is the coupling coefficient of the quality inspection of the i-th and j-th abnormal dimensions, t i and t j are the anomaly occurrence moments of the i-th anomaly dimension and the j-th anomaly dimension, respectively, and τ is the time constant;

[0105] Substituting each of the coupling coefficients into a third calculation formula to obtain each element value in a coupling matrix;

[0106] The third calculation formula is: , where M ij is the element value of the i-th row and j-th column in the coupling matrix, P i is the single-dimensional failure probability value of the i-th abnormal dimension, P j is the single-dimensional failure probability value of the j-th abnormal dimension;

[0107] A failure probability value of the air conditioner is calculated based on the coupling matrix.

[0108] Optionally, the probability value calculation module is further used to substitute the value of each element in the coupling matrix into a fourth calculation formula to obtain a comprehensive eigenvalue;

[0109] The fourth calculation formula is: , where S is the comprehensive eigenvalue;

[0110] Substituting the comprehensive characteristic value into the fifth calculation formula to obtain the failure probability value of the air conditioner;

[0111] The fifth calculation formula is: , where P is the failure probability value of the air conditioner and K is the preset adjustment coefficient.

[0112] Optionally, the detection result generating module is further used to obtain a preset fault feature library when the fault probability value is greater than a probability threshold, wherein the fault feature library includes multiple fault types and multiple groups of historical fluctuation characteristics corresponding to each fault type;

[0113] Matching the fluctuation characteristics of each abnormal dimension with the fault feature library to obtain a preliminary fault type;

[0114] A dimensional association model is established based on a preset air conditioning operation mechanism, wherein the dimensional association model is a physical coupling relationship and constraint conditions for quality inspection of each dimension;

[0115] The preliminary fault type is verified and supplemented according to the dimensional association model to obtain a target fault type, and a fault detection result including the target fault type is generated.

[0116] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0117] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing an air conditioner fault detection method of the above embodiment. The specific execution process can be found in the specific description of the above embodiment, which will not be repeated here.

[0118] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0119] The communication bus 302 is used to realize the connection and communication between these components.

[0120] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0121] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0122] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0123] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of an air conditioner fault detection method.

[0124] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program of a fault detection method of an air conditioner stored in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0125] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0127] 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.

[0128] 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0129] If the integrated unit 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 memory. Based on this understanding, the technical solution of the present application, 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, which is stored in a memory and includes several instructions for 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 memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0130] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0131] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for detecting a fault of an air conditioner, characterized in that: The method comprises: Obtain parameter values ​​corresponding to each dimension when the air conditioner is running, and determine the running state of the air conditioner based on the parameter values ​​corresponding to each dimension, wherein each dimension is at least one of pressure, temperature, current or rotation speed; When the operating state is initially abnormal, determining time series data of parameter values ​​corresponding to each dimension; Calculate the fluctuation amplitude, fluctuation frequency and fluctuation slope corresponding to each dimension according to the time series data of each dimension, wherein the fluctuation amplitude is the maximum deviation of the parameter value, the fluctuation frequency is the number of fluctuations of the parameter value per unit time, and the fluctuation slope is the average rate of change of the parameter value; Determine any dimension whose fluctuation amplitude exceeds the first threshold, whose fluctuation frequency exceeds the second threshold, or whose fluctuation slope exceeds the third threshold as an abnormal dimension, and use the fluctuation amplitude, fluctuation frequency and fluctuation slope of the abnormal dimension as fluctuation features; For any of the abnormal dimensions, calculating a first ratio of the fluctuation amplitude to the first threshold, a second ratio of the fluctuation frequency to the second threshold, and a third ratio of the fluctuation slope to the third threshold; Substituting the first ratio, the second ratio and the third ratio into a first calculation formula to obtain a single-dimensional failure probability value corresponding to each of the abnormal dimensions; Substituting each single-dimensional fault probability value into a second calculation formula to obtain a coupling coefficient between each dimension; Substituting each of the coupling coefficients into a third calculation formula to obtain each element value in a coupling matrix; Substituting each element value in the coupling matrix into the fourth calculation formula to obtain a comprehensive eigenvalue; Substituting the comprehensive characteristic value into the fifth calculation formula to obtain the failure probability value of the air conditioner; The first calculation formula is: ; Where Pi is the single-dimensional fault probability value of the i-th abnormal dimension, Ai is the first ratio, Fi is the second ratio, Ti is the third ratio, α, β, γ are preset weight coefficients, respectively. ; When the fault probability value is greater than the probability threshold, a preset fault feature library is obtained, wherein the fault feature library includes multiple fault types and multiple groups of historical fluctuation features corresponding to each of the fault types; Matching the fluctuation characteristics of each abnormal dimension with the fault feature library to obtain a preliminary fault type; A dimensional association model is established based on a preset air conditioning operation mechanism, wherein the dimensional association model is a physical coupling relationship and constraint conditions for quality inspection of each dimension; The preliminary fault type is verified and supplemented according to the dimensional association model to obtain a target fault type, and a fault detection result including the target fault type is generated.

2. The air conditioner fault detection method according to claim 1, characterized in that: The determining the operating state of the air conditioner based on the parameter values ​​corresponding to the dimensions includes: Obtaining the parameter change rate of the parameter value corresponding to each dimension within a preset time period; Determine the ratio between the parameter change rate of each dimension and the parameter change rate of an adjacent dimension; When any of the ratios exceeds the corresponding standard range, it is determined that the operating state of the air conditioner is initially abnormal.

3. The air conditioner fault detection method according to claim 1, characterized in that: The second calculation formula is: ; Where Rij is the coupling coefficient of the quality inspection of the i-th and j-th abnormal dimensions, ti and tj are the abnormal occurrence times of the i-th and j-th abnormal dimensions, respectively, and τ is the time constant; The third calculation formula is: , where Mij is the element value of the i-th row and j-th column in the coupling matrix, Pi is the single-dimensional failure probability value of the i-th abnormal dimension, and Pj is the single-dimensional failure probability value of the j-th abnormal dimension.

4. The air conditioner fault detection method according to claim 1, characterized in that: The fourth calculation formula is: , where S is the comprehensive eigenvalue; The fifth calculation formula is: , where P is the failure probability value of the air conditioner and K is the preset adjustment coefficient.

5. An air conditioner fault detection system for implementing the air conditioner fault detection method according to claims 1 to 4, characterized in that: The system comprises: An operating state determination module, used to obtain parameter values ​​corresponding to various dimensions when the air conditioner is running, and determine the operating state of the air conditioner based on the parameter values ​​corresponding to each dimension, wherein each dimension is at least one of pressure, temperature, current or rotation speed; A fluctuation characteristic determination module, used for determining the abnormal dimension and the fluctuation characteristic corresponding to each abnormal dimension based on the parameter value corresponding to each dimension when the operating state is initially abnormal; A probability value calculation module, used for performing fusion calculation on each of the fluctuation characteristics to obtain a failure probability value of the air conditioner; The detection result generating module is used to locate the fault based on each of the fluctuation characteristics when the fault probability value is greater than the probability threshold, so as to obtain the fault detection result of the air conditioner.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-4.

Images