Heating ventilation air conditioner fault identification method and system based on deep learning

Abstract

The invention discloses a heating ventilation air conditioner fault identification method and system based on deep learning, and belongs to the technical field of heating ventilation air conditioners, and the method comprises the following steps: S1, collecting operation data of heating ventilation air conditioner equipment; s2, cleaning and classifying the operation data of the heating, ventilation and air conditioning equipment, and constructing a fault identification model of the heating, ventilation and air conditioning equipment; s3, judging the real-time operation state of the heating, ventilation and air conditioning equipment according to the output result of the heating, ventilation and air conditioning equipment fault recognition model; and S4, when faults exist, timely fault early warning and maintenance management and control are carried out on the heating ventilation air conditioning equipment. The problem that the stability and reliability of the heating ventilation and air conditioning equipment are low due to the fact that real-time monitoring and fault recognition cannot be conducted on the heating ventilation and air conditioning equipment in the prior art is solved. According to the invention, real-time monitoring and fault identification can be carried out on the heating, ventilating and air conditioning equipment, faults of the heating, ventilating and air conditioning equipment can be found in time, early warning maintenance can be carried out on the heating, ventilating and air conditioning equipment in time, the stability and reliability of the heating, ventilating and air conditioning equipment can be improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of HVAC technology, and in particular to a HVAC fault identification method and system based on deep learning. Background Art

[0002] Due to the complex structure and harsh working environment of HVAC, various faults may occur during its long-term operation, causing great inconvenience to users.

[0003] Existing HVAC equipment cannot perform real-time monitoring and fault identification when in use, resulting in the failure to promptly detect HVAC equipment failures and the failure to promptly perform early warning maintenance on the HVAC equipment, resulting in low stability and reliability of the HVAC equipment and a poor user experience. Summary of the invention

[0004] The purpose of the present invention is to provide a HVAC fault identification method and system based on deep learning, which can perform real-time monitoring and fault identification of HVAC equipment, promptly discover HVAC equipment faults, and promptly perform early warning maintenance on HVAC equipment, thereby improving the stability and reliability of HVAC equipment, improving user experience, and solving the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The HVAC fault identification method based on deep learning includes the following steps:

[0007] S1: Collect the temperature, humidity and wind speed of the HVAC equipment in the actual operating environment to determine the HVAC equipment operating data;

[0008] S2: Clean and classify the HVAC equipment operation data into training set, test set and validation set. Based on the training set, train the deep learning model to determine the HVAC equipment fault identification model. Verify and test the HVAC equipment fault identification model based on the validation set and test set to determine the optimal HVAC equipment fault identification model based on deep learning.

[0009] S3: Analyze the real-time operation data of the HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judge the real-time operation status of the HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, and determine the HVAC equipment fault identification result based on deep learning;

[0010] S4: When the HVAC equipment fails, timely fault warning and maintenance control are carried out on the HVAC equipment to restore the HVAC equipment to normal operation in time.

[0011] According to another aspect of the present invention, a HVAC fault identification system based on deep learning is provided, which is used to implement the above-mentioned HVAC fault identification method based on deep learning, including:

[0012] Data acquisition module, used to collect HVAC equipment operation data;

[0013] The data processing module is used to clean and classify the HVAC equipment operation data and divide it into training set, test set and validation set;

[0014] Model building module, used to train deep learning models and build the optimal HVAC equipment fault identification model based on deep learning;

[0015] Fault identification module, used for automatic identification and early warning control of HVAC equipment faults;

[0016] Preferably, the data acquisition module comprises:

[0017] The temperature collection unit is used to collect the temperature of the HVAC equipment in the actual operating environment and obtain the temperature data of the HVAC equipment;

[0018] A humidity collection unit is used to collect the humidity conditions of the HVAC equipment in the actual operating environment and obtain the humidity data of the HVAC equipment;

[0019] A wind speed collection unit is used to collect the wind speed conditions of the HVAC equipment in the actual operating environment and obtain the wind speed data of the HVAC equipment;

[0020] Wherein, based on the HVAC equipment temperature data, the HVAC equipment humidity data and the HVAC equipment wind speed data, the HVAC equipment operation data is determined;

[0021] Among them, the HVAC equipment operation data includes the HVAC equipment normal operation data and the HVAC equipment failure data.

[0022] Preferably, the data acquisition module further includes:

[0023] A temperature data comparison module is used to collect temperature data in real time and compare the temperature data with a preset temperature data threshold;

[0024] A wind speed and humidity data extraction module, used to retrieve the real-time collected humidity data and the real-time collected wind speed data when the temperature data exceeds a preset temperature data threshold;

[0025] A first environmental parameter acquisition module, used to acquire a first environmental parameter by using the real-time collected humidity data in combination with the real-time collected temperature data;

[0026] Wherein, the first environmental parameter is obtained by the following formula:

[0027]

[0028] Among them, K 01 represents the first environmental parameter; n represents the number of times the temperature data is collected; m represents the number of times the humidity data is collected; T i represents the temperature value corresponding to the i-th temperature collection; T bi represents the standard deviation of the temperature value corresponding to the i-th temperature collection; W b W represents the standard deviation of humidity data corresponding to the collection time of the i-th temperature collection; i represents the humidity value corresponding to the i-th humidity collection; W bi represents the standard deviation of humidity values ​​corresponding to the i-th humidity collection; T b Indicates the standard deviation of the temperature data corresponding to the collection time of the i-th humidity collection;

[0029] A second environmental parameter acquisition module, used to acquire a second environmental parameter by using the real-time collected wind speed data in combination with the real-time collected temperature data;

[0030] Wherein, the second environmental parameter is obtained by the following formula:

[0031]

[0032] Among them, K 02 represents the second environmental parameter; n represents the number of times the temperature data is collected; k represents the number of times the wind speed data is collected; T i represents the temperature value corresponding to the i-th temperature collection; T bi represents the standard deviation of the temperature value corresponding to the i-th temperature collection; W b V represents the standard deviation of humidity data corresponding to the collection time of the i-th temperature collection; b W represents the standard deviation of wind speed data corresponding to the collection time of the i-th temperature collection; bv represents the standard deviation of humidity data corresponding to the collection time of the i-th wind speed collection; T bv V represents the standard deviation of the temperature data corresponding to the collection time of the i-th wind speed collection; i represents the wind speed value corresponding to the i-th wind speed collection; V bi Indicates the standard deviation of the wind speed value corresponding to the i-th wind speed collection;

[0033] The frequency adjustment determination module is used to compare the first environmental parameter with a preset first environmental parameter threshold, and at the same time, compare the second environmental parameter with a preset second environmental parameter threshold, and determine whether it is necessary to adjust the data collection frequency of the humidity collection unit and the wind speed collection unit according to the comparison result.

[0034] Preferably, the frequency adjustment determination module includes:

[0035] A first determination module, configured to determine that the data acquisition frequency of the wind speed acquisition unit needs to be adjusted when the first environmental parameter exceeds a preset first environmental parameter threshold and the second environmental parameter exceeds a preset second environmental parameter threshold;

[0036] A first frequency adjustment module, configured to adjust the data collection frequency of the wind speed collection unit by using the first environmental parameter and the second environmental parameter, and obtain the adjusted data collection frequency of the wind speed collection unit;

[0037] The adjusted data collection frequency of the wind speed collection unit is obtained by the following formula:

[0038]

[0039] Among them, F vt Indicates the adjusted data collection frequency of the wind speed collection unit; F v0 Indicates the data collection frequency of the wind speed collection unit before adjustment; K 01 Represents the first environmental parameter; K 02 represents the second environmental parameter;

[0040] A second determination module, configured to determine that the data acquisition frequency of the humidity acquisition unit needs to be adjusted when the first environmental parameter exceeds a preset first environmental parameter threshold, or when the second environmental parameter exceeds a preset second environmental parameter threshold;

[0041] A target environmental parameter determination module, used to take an environmental parameter exceeding a corresponding environmental parameter threshold as a target environmental parameter;

[0042] A second frequency adjustment module, used to adjust the data acquisition frequency of the humidity acquisition unit by using the target environmental parameter to obtain the adjusted data acquisition frequency of the humidity acquisition unit;

[0043] The adjusted data collection frequency of the humidity collection unit is obtained by the following formula:

[0044]

[0045] Among them, F wt Indicates the adjusted data collection frequency of the humidity collection unit; Fw0 Indicates the data collection frequency of the humidity collection unit before adjustment; K m Represents the target environment parameter; K 01 Represents the first environmental parameter; K 02 Represents the second environmental parameter.

[0046] Preferably, the data processing module includes:

[0047] A data cleaning unit, used to clean the HVAC equipment operation data;

[0048] Obtain HVAC equipment operation data;

[0049] Conduct consistency checks on HVAC equipment operating data;

[0050] According to the data consistency requirements, check whether there is inconsistent data in the HVAC equipment operation data that is useless for HVAC fault identification. If there is inconsistent data, remove the inconsistent data in the HVAC equipment operation data;

[0051] Check the invalid and missing values ​​of HVAC equipment operation data;

[0052] According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​in the HVAC equipment operation data that are useless for HVAC fault identification. If there are invalid values ​​and missing values, remove the invalid values ​​and missing values ​​in the HVAC equipment operation data;

[0053] Identify HVAC equipment operating data useful for HVAC fault identification.

[0054] Preferably, the data processing module further includes:

[0055] A data classification unit, used to classify the HVAC equipment operation data after cleaning;

[0056] Obtain HVAC equipment operating data useful for HVAC fault identification;

[0057] Classify HVAC equipment operation data useful for HVAC fault identification, and divide the HVAC equipment operation data into a training set, a test set, and a validation set;

[0058] Among them, the division ratio of training set, test set and validation set is 7:3:1;

[0059] The training set is used to train the deep learning model and determine the HVAC equipment fault identification model;

[0060] The test set is used to perform performance testing on the trained HVAC equipment fault identification model and evaluate the performance of the trained HVAC equipment fault identification model;

[0061] The validation set is used to verify the trained HVAC equipment fault identification model and adjust the model parameters.

[0062] Preferably, the model building module includes:

[0063] Model training unit, used to train deep learning models;

[0064] Get the training set;

[0065] The training set is input into the deep learning model, and the deep learning model automatically learns the characteristic differences between the normal operating state and the fault state of the HVAC equipment according to the input training set, and determines the HVAC equipment fault identification model;

[0066] A model verification unit, used to verify the fault identification model of HVAC equipment;

[0067] Obtain the trained HVAC equipment fault identification model;

[0068] Input the validation set into the trained HVAC equipment fault identification model, verify the trained HVAC equipment fault identification model based on the validation set, judge the performance of the HVAC equipment fault identification model, and adjust the hyperparameters of the HVAC equipment fault identification model;

[0069] A model testing unit, used to test the fault identification model of HVAC equipment;

[0070] Obtain verified HVAC equipment fault identification models;

[0071] Input the test set into the verified HVAC equipment fault recognition model, test the verified HVAC equipment fault recognition model based on the test set, and evaluate the performance of the trained HVAC equipment fault recognition model;

[0072] Determine the optimal deep learning-based model for HVAC equipment fault identification.

[0073] Preferably, the fault identification module includes:

[0074] A real-time monitoring unit is used to monitor the operating status of the HVAC equipment in the actual operating environment in real time and collect the real-time operating data of the HVAC equipment;

[0075] A fault identification unit for automatically identifying faults in HVAC equipment;

[0076] Obtain the best deep learning-based HVAC equipment fault identification model;

[0077] Deploy the optimal deep learning-based HVAC equipment fault identification model in the actual operating environment of HVAC equipment;

[0078] Analyze the real-time operation data of HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judge the real-time operation status of HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, and determine the HVAC equipment fault identification result based on deep learning;

[0079] Among them, the HVAC equipment fault identification result based on deep learning is that the HVAC equipment has fault behavior or the HVAC equipment does not have fault behavior.

[0080] Preferably, the fault identification module further includes:

[0081] Fault warning unit, used to provide early warning and control of fault behaviors of HVAC equipment;

[0082] Obtain HVAC equipment fault identification results based on deep learning;

[0083] When the HVAC equipment fails, timely fault warning and maintenance control will be carried out on the HVAC equipment, and warning information will be transmitted to the maintenance personnel in a timely manner. The maintenance personnel will be intelligently guided to carry out timely repairs on the HVAC equipment, so that the HVAC equipment can be restored to normal operation in time.

[0084] Compared with the prior art, the present invention has the following beneficial effects:

[0085] 1. The present invention collects the operating data of HVAC equipment, cleans and classifies the operating data of HVAC equipment, and divides the data into a training set, a test set, and a validation set. Based on the training set, a deep learning model is trained to determine a HVAC equipment fault identification model. The HVAC equipment fault identification model is verified and tested based on the validation set and the test set to determine the optimal HVAC equipment fault identification model based on deep learning.

[0086] 2. The present invention analyzes the real-time operation data of HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judges the real-time operation status of the HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, determines the HVAC equipment fault identification result based on deep learning, and when the HVAC equipment has fault behavior, timely fault warning and maintenance control are carried out on the HVAC equipment, so that the HVAC equipment can be restored to normal operation in time. The HVAC equipment can be monitored and fault identified in real time, the HVAC equipment can be discovered in time, and the HVAC equipment fault can be warned and maintained in time, which can improve the stability and reliability of the HVAC equipment and enhance the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 is a flow chart of a HVAC fault identification method based on deep learning of the present invention;

[0088] Figure 2 This is a structural framework diagram of the HVAC fault identification system based on deep learning of the present invention. DETAILED DESCRIPTION

[0089] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0090] In order to solve the problem that the existing HVAC equipment cannot be monitored in real time and fault identification cannot be performed during use, resulting in the failure to detect HVAC equipment failure in time, the failure to perform early warning maintenance on HVAC equipment in time, resulting in low stability and reliability of HVAC equipment and poor user experience, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0091] A HVAC fault identification system based on deep learning includes: a data acquisition module, a data processing module, a model building module and a fault identification module.

[0092] It should be noted that the data acquisition module is used to collect the operating data of the HVAC equipment; the data processing module is used to clean and classify the operating data of the HVAC equipment and divide it into training set, test set and validation set; the model building module is used to train the deep learning model and build the optimal HVAC equipment fault identification model based on deep learning; the fault identification module is used to automatically identify and pre-warn the faults of the HVAC equipment, and the HVAC equipment can be monitored and identified in real time, and the HVAC equipment can be detected in time. The faults can be pre-warned and maintained in time, which can improve the stability and reliability of the HVAC equipment and enhance the user experience.

[0093] In this embodiment, the data acquisition module includes:

[0094] The temperature collection unit is used to collect the temperature of the HVAC equipment in the actual operating environment and obtain the temperature data of the HVAC equipment;

[0095] It should be noted that a temperature sensor is configured on the HVAC equipment, and the temperature condition of the HVAC equipment in the actual operating environment is collected through the temperature sensor to obtain the temperature data of the HVAC equipment.

[0096] A humidity collection unit is used to collect the humidity conditions of the HVAC equipment in the actual operating environment and obtain the humidity data of the HVAC equipment;

[0097] It should be noted that a humidity sensor is configured on the HVAC equipment, and the humidity condition of the HVAC equipment in the actual operating environment is collected through the humidity sensor to obtain the humidity data of the HVAC equipment.

[0098] A wind speed collection unit is used to collect the wind speed conditions of the HVAC equipment in the actual operating environment and obtain the wind speed data of the HVAC equipment;

[0099] It should be noted that a wind speed sensor is configured on the HVAC equipment, and the wind speed conditions of the HVAC equipment in the actual operating environment are collected through the wind speed sensor to obtain the wind speed data of the HVAC equipment.

[0100] Wherein, based on the HVAC equipment temperature data, the HVAC equipment humidity data and the HVAC equipment wind speed data, the HVAC equipment operation data is determined;

[0101] Among them, the HVAC equipment operation data includes the HVAC equipment normal operation data and the HVAC equipment failure data.

[0102] Specifically, the data acquisition module further includes:

[0103] A temperature data comparison module is used to collect temperature data in real time and compare the temperature data with a preset temperature data threshold;

[0104] A wind speed and humidity data extraction module, used to retrieve the real-time collected humidity data and the real-time collected wind speed data when the temperature data exceeds a preset temperature data threshold;

[0105] A first environmental parameter acquisition module, used to acquire a first environmental parameter by using the real-time collected humidity data in combination with the real-time collected temperature data;

[0106] Wherein, the first environmental parameter is obtained by the following formula:

[0107]

[0108] Among them, K 01 represents the first environmental parameter; n represents the number of times the temperature data is collected; m represents the number of times the humidity data is collected; T i represents the temperature value corresponding to the i-th temperature collection; T bi represents the standard deviation of the temperature value corresponding to the i-th temperature collection; W b W represents the standard deviation of humidity data corresponding to the collection time of the i-th temperature collection; i represents the humidity value corresponding to the i-th humidity collection; W bi represents the standard deviation of humidity values ​​corresponding to the i-th humidity collection; T b Indicates the standard deviation of the temperature data corresponding to the collection time of the i-th humidity collection;

[0109] A second environmental parameter acquisition module, used to acquire a second environmental parameter by using the real-time collected wind speed data in combination with the real-time collected temperature data;

[0110] Wherein, the second environmental parameter is obtained by the following formula:

[0111]

[0112] Among them, K 02 represents the second environmental parameter; n represents the number of times the temperature data is collected; k represents the number of times the wind speed data is collected; T i represents the temperature value corresponding to the i-th temperature collection; T bi represents the standard deviation of the temperature value corresponding to the i-th temperature collection; W b V represents the standard deviation of humidity data corresponding to the collection time of the i-th temperature collection; b W represents the standard deviation of wind speed data corresponding to the collection time of the i-th temperature collection; bv represents the standard deviation of humidity data corresponding to the collection time of the i-th wind speed collection; Tbv V represents the standard deviation of the temperature data corresponding to the collection time of the i-th wind speed collection; i represents the wind speed value corresponding to the i-th wind speed collection; V bi Indicates the standard deviation of the wind speed value corresponding to the i-th wind speed collection;

[0113] The frequency adjustment determination module is used to compare the first environmental parameter with a preset first environmental parameter threshold, and at the same time, compare the second environmental parameter with a preset second environmental parameter threshold, and determine whether it is necessary to adjust the data collection frequency of the humidity collection unit and the wind speed collection unit according to the comparison result.

[0114] The technical effect of the above technical solution is: through the temperature data comparison module, the ambient temperature can be monitored in real time, and the subsequent data collection and processing process can be triggered when the temperature exceeds the preset threshold. This helps to detect abnormal environmental conditions in a timely manner and provide data support for the early warning system. The acquisition of the first environmental parameter and the second environmental parameter combines multiple environmental factors such as temperature, humidity and wind speed, and comprehensively considers the interaction between these factors through complex calculation formulas. This comprehensive evaluation helps to more accurately reflect the overall condition of the environment and provide more comprehensive information for environmental management and decision-making. According to the comparison results of the first environmental parameter and the second environmental parameter with the preset threshold, the frequency adjustment determination module can dynamically adjust the collection frequency of humidity and wind speed data. This means that when the environment is relatively stable, the data collection frequency can be reduced to save resources; when the environment changes drastically or approaches a critical state, the data collection frequency can be increased to obtain more accurate data, thereby improving the sensitivity and accuracy of monitoring. By dynamically adjusting the data collection frequency, the technical solution can optimize resource usage and reduce unnecessary data collection and processing overhead while ensuring the monitoring effect. This helps to improve the efficiency and sustainability of the entire data collection system. The design of the technical solution has certain flexibility and scalability. For example, the preset temperature, humidity and wind speed data thresholds can be adjusted according to actual needs, and the calculation formula of environmental parameters can be modified. In addition, the monitoring and processing functions of other environmental factors can be added as needed to meet more complex environmental monitoring needs.

[0115] In summary, this technical solution achieves accurate monitoring and efficient management of environmental conditions through real-time monitoring, comprehensive evaluation, and dynamic adjustment of data collection frequency. It has broad application prospects and important practical significance.

[0116] Specifically, the frequency adjustment determination module includes:

[0117] A first determination module, configured to determine that the data acquisition frequency of the wind speed acquisition unit needs to be adjusted when the first environmental parameter exceeds a preset first environmental parameter threshold and the second environmental parameter exceeds a preset second environmental parameter threshold;

[0118] A first frequency adjustment module, configured to adjust the data collection frequency of the wind speed collection unit by using the first environmental parameter and the second environmental parameter, and obtain the adjusted data collection frequency of the wind speed collection unit;

[0119] The adjusted data collection frequency of the wind speed collection unit is obtained by the following formula:

[0120]

[0121] Among them, F vt Indicates the adjusted data collection frequency of the wind speed collection unit; F v0 Indicates the data collection frequency of the wind speed collection unit before adjustment; K 01 Represents the first environmental parameter; K 02 represents the second environmental parameter;

[0122] A second determination module, configured to determine that the data acquisition frequency of the humidity acquisition unit needs to be adjusted when the first environmental parameter exceeds a preset first environmental parameter threshold, or when the second environmental parameter exceeds a preset second environmental parameter threshold;

[0123] A target environmental parameter determination module, used to take an environmental parameter exceeding a corresponding environmental parameter threshold as a target environmental parameter;

[0124] A second frequency adjustment module, used to adjust the data acquisition frequency of the humidity acquisition unit by using the target environmental parameter to obtain the adjusted data acquisition frequency of the humidity acquisition unit;

[0125] The adjusted data collection frequency of the humidity collection unit is obtained by the following formula:

[0126]

[0127] Among them, F wt Indicates the adjusted data collection frequency of the humidity collection unit; F w0 Indicates the data collection frequency of the humidity collection unit before adjustment; K m Represents the target environment parameter; K 01 Represents the first environmental parameter; K 02 Represents the second environmental parameter.

[0128] The technical effect of the above technical solution is: the technical solution can monitor the changes of environmental parameters in real time through the first determination module and the second determination module, and dynamically adjust the data collection frequency according to these changes. This dynamic adaptability helps to ensure that the data acquisition system can maintain the best monitoring effect under different environmental conditions. By comparing the first environmental parameter and the second environmental parameter with the preset threshold, the technical solution can more accurately determine when the data collection frequency needs to be adjusted. This accuracy helps to reduce unnecessary data collection while ensuring that important data can be captured in time when the environment changes. By adjusting the data collection frequency, the technical solution can optimize resource usage while ensuring the monitoring effect. When the environment is relatively stable, the data collection frequency can be reduced to reduce the demand for data storage and processing; when the environment changes drastically, the data collection frequency can be increased to ensure the accuracy and integrity of the data. The frequency adjustment formula in the technical solution is very flexible. This flexibility helps to meet the needs of different application scenarios. The design of the technical solution has certain scalability.

[0129] In summary, this technical solution achieves accurate monitoring and efficient management of environmental conditions by dynamically adjusting the data collection frequency, which has broad application prospects and important practical significance. However, in practical applications, the frequency adjustment formula needs to be further optimized and improved to ensure its accuracy and reliability.

[0130] In this embodiment, the data processing module includes:

[0131] A data cleaning unit, used to clean the HVAC equipment operation data;

[0132] Obtain HVAC equipment operation data;

[0133] Conduct consistency checks on HVAC equipment operating data;

[0134] According to the data consistency requirements, check whether there is inconsistent data in the HVAC equipment operation data that is useless for HVAC fault identification. If there is inconsistent data, remove the inconsistent data in the HVAC equipment operation data;

[0135] Check the invalid and missing values ​​of HVAC equipment operation data;

[0136] According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​in the HVAC equipment operation data that are useless for HVAC fault identification. If there are invalid values ​​and missing values, remove the invalid values ​​and missing values ​​in the HVAC equipment operation data;

[0137] Identify HVAC equipment operating data useful for HVAC fault identification.

[0138] It should be noted that data cleaning refers to the process of processing and organizing raw data during data analysis to improve the quality and availability of data.

[0139] Among them, consistency check is to check whether the data meets the requirements based on the reasonable value range or mutual relationship of each parameter, and find out the data that exceeds the normal range, is logically unreasonable or contradictory. For example, the variable measured by the 1-7 scale has a value of 0, and the weight has a negative number, which should be regarded as exceeding the normal value range; computer software such as SPSS, SAS and Excel can automatically identify each variable value that exceeds the range according to the defined value range; logically inconsistent answers may appear in many forms: for example, many respondents said that they drove to work, but reported that they did not have a car; or the respondents reported that they were heavy buyers and users of a certain brand, but at the same time gave a very low score on the familiarity scale.

[0140] In this embodiment, the data processing module further includes:

[0141] A data classification unit, used to classify the HVAC equipment operation data after cleaning;

[0142] Obtain HVAC equipment operating data useful for HVAC fault identification;

[0143] Classify HVAC equipment operation data useful for HVAC fault identification, and divide the HVAC equipment operation data into a training set, a test set, and a validation set;

[0144] Among them, the division ratio of training set, test set and validation set is 7:3:1;

[0145] The training set is used to train the deep learning model and determine the HVAC equipment fault identification model;

[0146] The test set is used to perform performance testing on the trained HVAC equipment fault identification model and evaluate the performance of the trained HVAC equipment fault identification model;

[0147] The validation set is used to verify the trained HVAC equipment fault identification model and adjust the model parameters.

[0148] In this embodiment, the model building module includes:

[0149] Model training unit, used to train deep learning models;

[0150] Get the training set;

[0151] The training set is input into the deep learning model, and the deep learning model automatically learns the characteristic differences between the normal operating state and the fault state of the HVAC equipment according to the input training set, and determines the HVAC equipment fault identification model;

[0152] A model verification unit, used to verify the fault identification model of HVAC equipment;

[0153] Obtain the trained HVAC equipment fault identification model;

[0154] Input the validation set into the trained HVAC equipment fault identification model, verify the trained HVAC equipment fault identification model based on the validation set, judge the performance of the HVAC equipment fault identification model, and adjust the hyperparameters of the HVAC equipment fault identification model;

[0155] A model testing unit, used to test the fault identification model of HVAC equipment;

[0156] Obtain verified HVAC equipment fault identification models;

[0157] Input the test set into the verified HVAC equipment fault recognition model, test the verified HVAC equipment fault recognition model based on the test set, and evaluate the performance of the trained HVAC equipment fault recognition model;

[0158] Determine the optimal deep learning-based model for HVAC equipment fault identification.

[0159] In this embodiment, the fault identification module includes:

[0160] A real-time monitoring unit is used to monitor the operating status of the HVAC equipment in the actual operating environment in real time and collect the real-time operating data of the HVAC equipment;

[0161] A fault identification unit for automatically identifying faults in HVAC equipment;

[0162] Obtain the best deep learning-based HVAC equipment fault identification model;

[0163] Deploy the optimal deep learning-based HVAC equipment fault identification model in the actual operating environment of HVAC equipment;

[0164] Analyze the real-time operation data of HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judge the real-time operation status of HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, and determine the HVAC equipment fault identification result based on deep learning;

[0165] Among them, the HVAC equipment fault identification result based on deep learning is that the HVAC equipment has fault behavior or the HVAC equipment does not have fault behavior.

[0166] It should be noted that the real-time operation data of the HVAC equipment is analyzed through the optimal HVAC equipment fault identification model based on deep learning. The real-time operation status of the HVAC equipment is judged according to the output results of the optimal HVAC equipment fault identification model based on deep learning. When the HVAC equipment has fault behavior, the HVAC equipment is promptly warned of faults and maintained and controlled, and the warning information is promptly transmitted to the maintenance personnel. The maintenance personnel are intelligently guided to carry out timely repairs on the HVAC equipment, so that the HVAC equipment can be restored to normal operation in time, which can improve the stability and reliability of the HVAC equipment and enhance the user experience.

[0167] In this embodiment, the fault identification module further includes:

[0168] Fault warning unit, used to provide early warning and control of fault behaviors of HVAC equipment;

[0169] Obtain HVAC equipment fault identification results based on deep learning;

[0170] When the HVAC equipment fails, timely fault warning and maintenance control will be carried out on the HVAC equipment, and warning information will be transmitted to the maintenance personnel in a timely manner. The maintenance personnel will be intelligently guided to carry out timely repairs on the HVAC equipment, so that the HVAC equipment can be restored to normal operation in time.

[0171] In order to better demonstrate the HVAC fault identification process based on deep learning, this embodiment now provides a HVAC fault identification method based on deep learning, which is implemented based on the above-mentioned HVAC fault identification system based on deep learning, including the following steps:

[0172] S1: Collect the temperature, humidity and wind speed of the HVAC equipment in the actual operating environment to determine the HVAC equipment operating data;

[0173] S2: Clean and classify the HVAC equipment operation data into training set, test set and validation set. Based on the training set, train the deep learning model to determine the HVAC equipment fault identification model. Verify and test the HVAC equipment fault identification model based on the validation set and test set to determine the optimal HVAC equipment fault identification model based on deep learning.

[0174] S3: Analyze the real-time operation data of the HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judge the real-time operation status of the HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, and determine the HVAC equipment fault identification result based on deep learning;

[0175] S4: When the HVAC equipment fails, timely fault warning and maintenance control are carried out on the HVAC equipment to restore the HVAC equipment to normal operation in time.

[0176] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0177] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A HVAC fault identification method based on deep learning, characterized in that: The steps include: S1: Collect the temperature, humidity and wind speed of the HVAC equipment in the actual operating environment to determine the HVAC equipment operating data; S2: Clean and classify the HVAC equipment operation data into training set, test set and validation set. Based on the training set, train the deep learning model to determine the HVAC equipment fault identification model. Verify and test the HVAC equipment fault identification model based on the validation set and test set to determine the optimal HVAC equipment fault identification model based on deep learning. S3: Analyze the real-time operation data of the HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judge the real-time operation status of the HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, and determine the HVAC equipment fault identification result based on deep learning; S4: When the HVAC equipment fails, timely fault warning and maintenance control are carried out on the HVAC equipment to restore the HVAC equipment to normal operation in time.

2. A HVAC fault identification system based on deep learning, used to implement the HVAC fault identification method based on deep learning as claimed in claim 1, characterized in that: include: Data acquisition module, used to collect HVAC equipment operation data; The data processing module is used to clean and classify the HVAC equipment operation data and divide it into training set, test set and validation set; Model building module, used to train deep learning models and build the optimal HVAC equipment fault identification model based on deep learning; The fault identification module is used to automatically identify and pre-warn faults of HVAC equipment.

3. The HVAC fault identification system based on deep learning according to claim 2, characterized in that: The data acquisition module comprises: The temperature collection unit is used to collect the temperature of the HVAC equipment in the actual operating environment and obtain the temperature data of the HVAC equipment; A humidity collection unit is used to collect the humidity conditions of the HVAC equipment in the actual operating environment and obtain the humidity data of the HVAC equipment; A wind speed collection unit is used to collect the wind speed conditions of the HVAC equipment in the actual operating environment and obtain the wind speed data of the HVAC equipment; Wherein, based on the HVAC equipment temperature data, the HVAC equipment humidity data and the HVAC equipment wind speed data, the HVAC equipment operation data is determined; Among them, the HVAC equipment operation data includes the HVAC equipment normal operation data and the HVAC equipment failure data.

4. The HVAC fault identification system based on deep learning according to claim 3, characterized in that: The data acquisition module further includes: A temperature data comparison module is used to collect temperature data in real time and compare the temperature data with a preset temperature data threshold; A wind speed and humidity data extraction module, used to retrieve the real-time collected humidity data and the real-time collected wind speed data when the temperature data exceeds a preset temperature data threshold; A first environmental parameter acquisition module, used to acquire a first environmental parameter by using the real-time collected humidity data in combination with the real-time collected temperature data; Wherein, the first environmental parameter is obtained by the following formula: Among them, K 01 represents the first environmental parameter; n represents the number of times the temperature data is collected; m represents the number of times the humidity data is collected; T i represents the temperature value corresponding to the i-th temperature collection; T bi represents the standard deviation of the temperature value corresponding to the i-th temperature collection; W b W represents the standard deviation of humidity data corresponding to the collection time of the i-th temperature collection; i represents the humidity value corresponding to the i-th humidity collection; W bi represents the standard deviation of humidity values ​​corresponding to the i-th humidity collection; T b Indicates the standard deviation of the temperature data corresponding to the collection time of the i-th humidity collection; A second environmental parameter acquisition module, used to acquire a second environmental parameter by using the real-time collected wind speed data in combination with the real-time collected temperature data; Wherein, the second environmental parameter is obtained by the following formula; Among them, K 02 represents the second environmental parameter; n represents the number of times the temperature data is collected; k represents the number of times the wind speed data is collected; T i represents the temperature value corresponding to the i-th temperature collection; T bi represents the standard deviation of the temperature value corresponding to the i-th temperature collection; W b V represents the standard deviation of humidity data corresponding to the collection time of the i-th temperature collection; b W represents the standard deviation of wind speed data corresponding to the collection time of the i-th temperature collection; bv represents the standard deviation of humidity data corresponding to the collection time of the i-th wind speed collection; T bv V represents the standard deviation of the temperature data corresponding to the collection time of the i-th wind speed collection; i represents the wind speed value corresponding to the i-th wind speed collection; V bi Indicates the standard deviation of the wind speed value corresponding to the i-th wind speed collection; The frequency adjustment determination module is used to compare the first environmental parameter with a preset first environmental parameter threshold, and at the same time, compare the second environmental parameter with a preset second environmental parameter threshold, and determine whether it is necessary to adjust the data collection frequency of the humidity collection unit and the wind speed collection unit according to the comparison result.

5. The HVAC fault identification system based on deep learning according to claim 4, characterized in that: The frequency adjustment determination module includes: A first determination module, configured to determine that the data acquisition frequency of the wind speed acquisition unit needs to be adjusted when the first environmental parameter exceeds a preset first environmental parameter threshold and the second environmental parameter exceeds a preset second environmental parameter threshold; A first frequency adjustment module, configured to adjust the data collection frequency of the wind speed collection unit by using the first environmental parameter and the second environmental parameter, and obtain the adjusted data collection frequency of the wind speed collection unit; The adjusted data collection frequency of the wind speed collection unit is obtained by the following formula: Among them, F vt Indicates the adjusted data collection frequency of the wind speed collection unit; F v0 Indicates the data collection frequency of the wind speed collection unit before adjustment; K 01 Represents the first environmental parameter; K 02 represents the second environmental parameter; A second determination module, configured to determine that the data acquisition frequency of the humidity acquisition unit needs to be adjusted when the first environmental parameter exceeds a preset first environmental parameter threshold, or when the second environmental parameter exceeds a preset second environmental parameter threshold; A target environmental parameter determination module, used to take an environmental parameter exceeding a corresponding environmental parameter threshold as a target environmental parameter; A second frequency adjustment module, used to adjust the data acquisition frequency of the humidity acquisition unit by using the target environmental parameter to obtain the adjusted data acquisition frequency of the humidity acquisition unit; The adjusted data collection frequency of the humidity collection unit is obtained by the following formula: Among them, F wt Indicates the adjusted data collection frequency of the humidity collection unit; F w0 Indicates the data collection frequency of the humidity collection unit before adjustment; K m Represents the target environment parameter; K 01 Represents the first environmental parameter; K 02 Represents the second environmental parameter.

6. The HVAC fault identification system based on deep learning according to claim 3, characterized in that: The data processing module comprises: A data cleaning unit, used to clean the HVAC equipment operation data; Obtain HVAC equipment operation data; Conduct consistency checks on HVAC equipment operating data; According to the data consistency requirements, check whether there is inconsistent data in the HVAC equipment operation data that is useless for HVAC fault identification. If there is inconsistent data, remove the inconsistent data in the HVAC equipment operation data; Check the invalid and missing values ​​of HVAC equipment operation data; According to the requirements of data validity and integrity, check whether there are invalid values ​​and missing values ​​in the HVAC equipment operation data that are useless for HVAC fault identification. If there are invalid values ​​and missing values, remove the invalid values ​​and missing values ​​in the HVAC equipment operation data; Identify HVAC equipment operating data useful for HVAC fault identification.

7. The HVAC fault identification system based on deep learning according to claim 6, characterized in that: The data processing module further includes: A data classification unit, used to classify the HVAC equipment operation data after cleaning; Obtain HVAC equipment operating data useful for HVAC fault identification; Classify HVAC equipment operation data useful for HVAC fault identification, and divide the HVAC equipment operation data into a training set, a test set, and a validation set; Among them, the division ratio of training set, test set and validation set is 7:3:1; The training set is used to train the deep learning model and determine the HVAC equipment fault identification model; The test set is used to perform performance testing on the trained HVAC equipment fault identification model and evaluate the performance of the trained HVAC equipment fault identification model; The validation set is used to verify the trained HVAC equipment fault identification model and adjust the model parameters.

8. The HVAC fault identification system based on deep learning according to claim 7, characterized in that: The model building module comprises: Model training unit, used to train deep learning models; Get the training set; The training set is input into the deep learning model, and the deep learning model automatically learns the characteristic differences between the normal operating state and the fault state of the HVAC equipment according to the input training set, and determines the HVAC equipment fault identification model; A model verification unit, used to verify the fault identification model of HVAC equipment; Obtain the trained HVAC equipment fault identification model; Input the validation set into the trained HVAC equipment fault identification model, verify the trained HVAC equipment fault identification model based on the validation set, judge the performance of the HVAC equipment fault identification model, and adjust the hyperparameters of the HVAC equipment fault identification model; A model testing unit, used to test the fault identification model of HVAC equipment; Obtain verified HVAC equipment fault identification models; Input the test set into the verified HVAC equipment fault recognition model, test the verified HVAC equipment fault recognition model based on the test set, and evaluate the performance of the trained HVAC equipment fault recognition model; Determine the optimal deep learning-based model for HVAC equipment fault identification.

9. The HVAC fault identification system based on deep learning according to claim 8, characterized in that: The fault identification module comprises: A real-time monitoring unit is used to monitor the operating status of the HVAC equipment in the actual operating environment in real time and collect the real-time operating data of the HVAC equipment; A fault identification unit for automatically identifying faults in HVAC equipment; Obtain the best deep learning-based HVAC equipment fault identification model; Deploy the optimal deep learning-based HVAC equipment fault identification model in the actual operating environment of HVAC equipment; Analyze the real-time operation data of HVAC equipment through the optimal HVAC equipment fault identification model based on deep learning, judge the real-time operation status of HVAC equipment according to the output result of the optimal HVAC equipment fault identification model based on deep learning, and determine the HVAC equipment fault identification result based on deep learning; Among them, the HVAC equipment fault identification result based on deep learning is that the HVAC equipment has fault behavior or the HVAC equipment does not have fault behavior.

10. The HVAC fault identification system based on deep learning according to claim 9, characterized in that: The fault identification module further includes: Fault warning unit, used to provide early warning and control of fault behaviors of HVAC equipment; Obtain HVAC equipment fault identification results based on deep learning; When the HVAC equipment fails, timely fault warning and maintenance control will be carried out on the HVAC equipment, and warning information will be transmitted to the maintenance personnel in a timely manner. The maintenance personnel will be intelligently guided to carry out timely repairs on the HVAC equipment, so that the HVAC equipment can be restored to normal operation in time.

Images