A method, device, computer equipment and system for detecting faults of a fan coil based on a temperature controller

Abstract

The application relates to a method and device for detecting faults of a fan coil based on a temperature controller, computer equipment and a system, the method comprising the following steps: acquiring real-time temperature data of any temperature controller associated with any fan coil in any central air conditioning system, the real-time temperature data reflecting the real-time outlet temperature of the fan coil; judging a first detection result of whether the fan coil is faulty; acquiring real-time fan gear data and real-time start-up duration data of the fan coil in the central air conditioning system, and converting the data into a to-be-detected data set in combination with a binary classification label of whether the fan coil is faulty; inputting the to-be-detected data set into a preset fan coil fault detection model to output a second detection result of whether the fan coil is faulty; and comprehensively combining the first detection result and the second detection result to output early warning information of the fan coil fault. The application has the effect of improving the fault detection accuracy of the fan coil.

Description

Technical Field

[0001] This application relates to the field of fan coil unit testing technology, and in particular to a method, apparatus, computer equipment and system for fault detection of fan coil units based on a temperature controller. Background Technology

[0002] Central air conditioning systems are essential in many places, such as offices, shopping malls, schools, and large buildings, and fan coil units are a key component for indoor temperature regulation. Fault detection in fan coil units primarily relies on solenoid valves controlling the on / off flow of hot and cold water. However, solenoid valves have a relatively high failure rate, and malfunctions in fan coil units often go undetected until user complaints or routine inspections reveal the problem. This not only impacts the user experience but also increases maintenance costs and time.

[0003] To address this, IoT functionality is designed into fan coil units. By integrating sensors and communication modules into the fan coil units, remote monitoring and alarm functions can be achieved with the help of external networks. However, this type of product requires additional hardware and software support, resulting in relatively high system costs and limited adoption.

[0004] Regarding the aforementioned technologies, the inventors have discovered a contradiction between the efficiency of fan coil unit fault detection and the cost of central air conditioning system products in existing fan coil unit fault detection methods. Summary of the Invention

[0005] To address the conflict between the efficiency of fan coil unit fault detection and the cost of central air conditioning system products, and to improve the efficiency of fan coil unit fault detection while reducing the cost of central air conditioning system products, this application provides a method, apparatus, computer equipment, and system for fault detection of fan coil units based on a thermostat.

[0006] Firstly, this application provides a method for fault detection of fan coil units based on a thermostat.

[0007] This application is achieved through the following technical solution:

[0008] A method for fault detection of fan coil units based on a thermostat includes the following steps:

[0009] Obtain real-time temperature data of any thermostat associated with any fan coil unit in any central air conditioning system, wherein the real-time temperature data is used to reflect the real-time outlet temperature of the fan coil unit.

[0010] Determine whether the real-time temperature data meets preset conditions, and output the first detection result of whether the fan coil unit is faulty;

[0011] And obtain the real-time fan speed data and real-time start-up duration data of the fan coil unit in the central air conditioning system to obtain the initial sequence data;

[0012] The initial sequence data is preprocessed and combined with binary classification labels indicating whether the fan coil unit is faulty to obtain the dataset to be detected.

[0013] Input the dataset to be detected into the preset fan coil unit fault detection model, and output a second detection result of whether the fan coil unit is faulty;

[0014] When the first prediction result is a fan coil unit failure and the second detection result is a fan coil unit failure, a warning message for a fan coil unit failure is issued.

[0015] The training steps for the fan coil unit fault detection model include:

[0016] Collect historical fan speed data and historical start-up duration data of the fan coil units in the central air conditioning system to obtain historical sequence data;

[0017] The historical sequence data is preprocessed and combined with binary classification labels indicating whether the fan coil unit is faulty to obtain a sample dataset.

[0018] The sample dataset is input into a deep learning model for training, and the detection result of whether the fan coil unit is faulty is output until the accuracy of the deep learning model meets the preset requirements, thus obtaining the fan coil unit fault detection model.

[0019] In a preferred embodiment, this application can be further configured as follows: the step of determining whether the real-time temperature data meets preset conditions and outputting a first detection result indicating whether the fan coil unit is faulty includes...

[0020] When the real-time temperature data is outside the preset temperature threshold range, the first detection result of the fan coil unit fault is output.

[0021] Alternatively, a trend curve of the outlet temperature of the fan coil unit can be plotted based on the real-time temperature data, and it can be determined whether the rate of temperature change within a preset time period on the trend curve is outside the preset temperature change range. When the rate of temperature change is outside the preset temperature change range, the first detection result of the fan coil unit fault can be output.

[0022] In a preferred embodiment, this application can be further configured such that the training steps of the fan coil unit fault detection model also include,

[0023] When collecting historical fan speed data and historical operating duration data of the fan coil units in the central air conditioning system, the data is collected periodically, and the collection results are updated to the historical sequence data.

[0024] The updated historical sequence data is preprocessed, and the data format is converted by combining the binary classification label of whether the fan coil unit is faulty, and the sample dataset is updated.

[0025] The updated sample dataset is input into the fan coil unit fault detection model for training, and the detection result of whether the fan coil unit is faulty is output, thus obtaining a new fan coil unit fault detection model.

[0026] The existing fan coil unit fault detection model is replaced with a new one.

[0027] In a preferred embodiment, this application can be further configured to include the following steps:

[0028] Acquire indoor temperature data in the same space as any central air conditioning system, wherein the indoor temperature data is used to reflect the temperature data of a target area of ​​the human body;

[0029] Set the difference between the equipment temperature data of the fan coil unit and the indoor temperature data;

[0030] When the indoor temperature drops to the same level as the equipment temperature, the hot and cold water valves are shut off.

[0031] When the indoor temperature rises to the sum of the difference between the device temperature and the indoor temperature, the hot and cold water valves are opened.

[0032] In a preferred embodiment, this application can be further configured to include the following steps:

[0033] The real-time temperature data and the early warning information are uploaded to the target monitoring center platform, which is used for centralized remote monitoring and early warning of the fan coil unit failure status of each central air conditioning system.

[0034] Secondly, this application provides a device for fault detection of fan coil units based on a temperature controller.

[0035] This application is achieved through the following technical solution:

[0036] A device for fault detection of fan coil units based on a thermostat, comprising,

[0037] The coil temperature acquisition module is used to acquire real-time temperature data of any thermostat associated with any fan coil unit in any central air conditioning system. The real-time temperature data is used to reflect the real-time outlet temperature of the fan coil unit.

[0038] The first detection module is used to determine whether the real-time temperature data meets the first preset condition and output the first detection result of whether the fan coil unit is faulty.

[0039] The initial sequence data module is used to obtain the real-time fan speed data and real-time start-up duration data of the fan coil unit in the central air conditioning system to obtain the initial sequence data;

[0040] The dataset to be detected module is used to preprocess the initial sequence data and combine it with the binary classification label of whether the fan coil unit is faulty to obtain the dataset to be detected;

[0041] The second detection module is used to input the dataset to be detected into a preset fan coil unit fault detection model and output a second detection result of whether the fan coil unit is faulty.

[0042] The early warning module is used to issue an early warning message for a fan coil unit failure when both the first prediction result and the second detection result indicate a fan coil unit failure.

[0043] The model module is used to collect historical fan speed data and historical operating time data of the fan coil units in the central air conditioning system to obtain historical sequence data; preprocess the historical sequence data and combine it with binary classification labels indicating whether the fan coil units are faulty to obtain a sample dataset; input the sample dataset into a deep learning model for training, and output the detection results of whether the fan coil units are faulty, until the accuracy of the deep learning model meets the preset requirements, thus obtaining the fan coil unit fault detection model.

[0044] In a preferred embodiment, this application can be further configured such that the model module also includes,

[0045] The historical sequence data update unit is used to collect historical fan speed data and historical start-up duration data of the fan coil units in the central air conditioning system in a periodic manner, and update the collection results to the historical sequence data.

[0046] The sample dataset update unit is used to preprocess the updated historical sequence data and perform data format conversion by combining the binary classification label of whether the fan coil unit is faulty, and update the sample dataset.

[0047] The model iteration unit is used to input the updated sample dataset into the fan coil unit fault detection model for training, and output the detection result of whether the fan coil unit is faulty, thus obtaining a new fan coil unit fault detection model.

[0048] The model replacement unit is used to replace the fan coil unit fault detection model with a new fan coil unit fault detection model.

[0049] In a preferred embodiment, this application may be further configured to include:

[0050] The indoor temperature data module is used to acquire indoor temperature data in the same space as any central air conditioning system. The indoor temperature data is used to reflect the temperature data of the target area of ​​the human body.

[0051] The temperature control hysteresis module is used to set the difference between the equipment temperature data of the fan coil unit and the indoor temperature data.

[0052] The first execution module is used to control the hot and cold water valves to close when the indoor temperature data drops to the same level as the equipment temperature data;

[0053] The second execution module is used to control the hot and cold water valves to open when the indoor temperature data rises to the sum of the difference between the device temperature data and the indoor temperature data.

[0054] Thirdly, this application provides a computer device.

[0055] This application is achieved through the following technical solution:

[0056] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the above-described methods for fault detection of fan coil units based on a temperature controller.

[0057] Fourthly, this application provides a fan coil unit fault detection system.

[0058] This application is achieved through the following technical solution:

[0059] A fan coil unit fault detection system includes any thermostat associated with any fan coil unit installed in any central air conditioning system, the thermostat including a data acquisition unit and a data processing unit;

[0060] The data acquisition unit is used to collect and send the attribute data of the fan coil unit. The attribute data includes the outlet temperature data of the fan coil unit, the fan speed data, and the fan start-up time data.

[0061] The data processing unit receives the attribute data sent by the data acquisition unit, determines whether the real-time outlet temperature of the fan coil unit meets the preset conditions, and outputs a first detection result indicating whether the fan coil unit is faulty; and runs a preset fan coil unit fault detection program to output a second detection result indicating whether the fan coil unit is faulty; when the first prediction result indicates that the fan coil unit is faulty and the second detection result indicates that the fan coil unit is faulty, the fan coil unit is determined to be faulty.

[0062] The fan coil unit fault detection program includes collecting historical fan speed data and historical operating duration data of the fan coil units in the central air conditioning system to obtain historical sequence data; preprocessing the historical sequence data and combining it with binary classification labels indicating whether the fan coil unit is faulty to obtain a sample dataset; inputting the sample dataset into a deep learning model for training, and outputting the detection result of whether the fan coil unit is faulty, until the accuracy of the deep learning model meets the preset requirements, thereby obtaining the fan coil unit fault detection model used to identify whether the fan coil unit is in a fault mode.

[0063] In summary, compared with the prior art, the beneficial effects of the technical solution provided in this application include at least the following:

[0064] By acquiring real-time temperature data from any thermostat associated with any fan coil unit in any central air conditioning system—which reflects the real-time outlet temperature of the target fan coil unit—the system can determine if the fan coil unit is faulty. This method directly utilizes the existing data acquisition and control command functions of the thermostat to detect fan coil unit faults without requiring modifications, thus reducing the product cost of the central air conditioning system. It also eliminates the need for manual inspections, enabling timely detection of fan coil unit faults and improving detection efficiency. Furthermore, the system acquires real-time fan speed data and real-time operating duration data for the fan coil units in the central air conditioning system to obtain initial sequence data. This initial sequence data is then preprocessed. The system combines binary labels indicating whether a fan coil unit is faulty to obtain a dataset for detection. This dataset is then input into a pre-defined fan coil unit fault detection model, which outputs a second detection result indicating whether the fan coil unit is faulty. This leverages a machine learning model to accurately identify fan coil unit faults, achieving intelligent early warning for fan coil unit faults with high detection efficiency and accuracy. Finally, when both the first prediction and second detection results indicate a fan coil unit fault, an early warning message is issued. By comprehensively judging the fault status of the fan coil unit based on the first and second detection results, the accuracy of fan coil unit fault detection is greatly improved. Attached Figure Description

[0065] Figure 1 This is a schematic diagram of the main process of a method for fault detection of fan coil units based on a thermostat, provided as an exemplary embodiment of this application.

[0066] Figure 2 A flowchart illustrating the temperature hysteresis of a method for fault detection of fan coil units based on a thermostat, which is another exemplary embodiment of this application.

[0067] Figure 3The main training flowchart of a fan coil unit fault detection model is provided as an exemplary embodiment of this application for a method of fault detection of fan coil units based on a thermostat.

[0068] Figure 4 A main architecture diagram of a fan coil unit fault detection system is provided for another exemplary embodiment of this application.

[0069] Figure 5 Another architecture diagram of a fan coil unit fault detection system provided for an exemplary embodiment of this application. Detailed Implementation

[0070] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0071] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0072] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0073] The existing technologies for detecting fan coil unit faults in current central air conditioning systems are as follows:

[0074] 1. Utilizing IoT technology: By integrating sensors and communication modules into the fan coil units of a central air conditioning system, the operating status of the equipment can be remotely monitored. However, this technology requires modifications to the fan coil units, necessitates additional hardware and software support, resulting in higher product costs for central air conditioning systems, and relies on external network connectivity.

[0075] 2. Regular inspection: The working status of the fan coil unit is checked by regular inspection. However, this method relies on manual labor and cannot monitor the status of the equipment in real time. It is difficult to detect the faults of the fan coil unit in the central air conditioning system in a timely manner. Some complex fault detection techniques require professional maintenance personnel to operate and manage, which makes maintenance difficult, repair time long, and affects the user experience.

[0076] 3. Current-based fault detection: This method infers the operating status of equipment by monitoring the motor current. While it is more sensitive to electrical faults, it has limited effectiveness in detecting mechanical faults (such as solenoid valve jamming). Current-based fan coil unit fault detection methods are easily affected by various factors, leading to misjudgments or missed diagnoses.

[0077] In view of the shortcomings of the prior art, this application aims to solve the following technical problems:

[0078] 1. Reduced costs: By utilizing the mature functions of existing thermostats, the need for additional modifications to the hardware and software systems of fan coil units is avoided, thereby reducing system costs and lowering the overall maintenance and operating costs of the system;

[0079] 2. Improved real-time performance: By monitoring temperature changes and temperature differences in real time, fan coil unit faults can be detected in a timely manner, thus improving the ability to monitor fan coil unit faults in real time.

[0080] 3. Improve accuracy: By combining the working status of the fan coil unit with the fault mode identification of the fan coil unit through machine model, or by comparing with historical data, the working status of the fan coil unit can be judged more accurately, reducing the possibility of misjudgment or omission of fan coil unit faults.

[0081] 4. Simplified maintenance: By providing a low-cost and efficient fault detection method, it can be operated and managed without the need for professional maintenance personnel, thus simplifying the maintenance process.

[0082] To address this, this application utilizes the control command and data acquisition functions of existing thermostats, combining two detection methods: the working status of the fan coil unit and the machine model's identification of the fan coil unit's fault modes. This enables a comprehensive judgment of fan coil unit faults in central air conditioning systems without requiring additional modifications to the fan coil units. This resolves the contradiction between fan coil unit fault detection efficiency and central air conditioning system product costs, improving fault detection efficiency, reducing central air conditioning system product costs, enhancing detection accuracy, and improving user experience.

[0083] The embodiments of this application will now be described in further detail with reference to the accompanying drawings.

[0084] Reference Figure 1This application provides a method for fault detection of fan coil units based on a thermostat. The main steps of the method are described below.

[0085] S11: Obtain real-time temperature data of any thermostat associated with any fan coil unit in any central air conditioning system, wherein the real-time temperature data is used to reflect the real-time outlet temperature of the fan coil unit.

[0086] S12: Determine whether the real-time temperature data meets the preset conditions, and output the first detection result of whether the fan coil unit is faulty;

[0087] S21: And obtain the real-time fan speed data and real-time start-up duration data of the fan coil unit in the central air conditioning system to obtain the initial sequence data;

[0088] S22: The initial sequence data is preprocessed and combined with the binary classification label of whether the fan coil unit is faulty to obtain the dataset to be detected;

[0089] S23: Input the dataset to be detected into the preset fan coil unit fault detection model, and output the second detection result of whether the fan coil unit is faulty;

[0090] S3: When the first prediction result is a fan coil unit failure and the second detection result is a fan coil unit failure, issue a warning message for a fan coil unit failure.

[0091] The training steps for the fan coil unit fault detection model include:

[0092] Collect historical fan speed data and historical start-up duration data of the fan coil units in the central air conditioning system to obtain historical sequence data;

[0093] The historical sequence data is preprocessed and combined with binary classification labels indicating whether the fan coil unit is faulty to obtain a sample dataset.

[0094] The sample dataset is input into a deep learning model for training, and the detection result of whether the fan coil unit is faulty is output until the accuracy of the deep learning model meets the preset requirements, thus obtaining the fan coil unit fault detection model.

[0095] In one embodiment, the step of determining whether the real-time temperature data meets preset conditions and outputting a first detection result indicating whether the fan coil unit is faulty includes:

[0096] When the real-time temperature data is outside the preset temperature threshold range, the first detection result of the fan coil unit fault is output.

[0097] Alternatively, a trend curve of the outlet temperature of the fan coil unit can be plotted based on the real-time temperature data, and it can be determined whether the rate of temperature change within a preset time period on the trend curve is outside the preset temperature change range. When the rate of temperature change is outside the preset temperature change range, the first detection result of the fan coil unit fault can be output.

[0098] In one embodiment, the training step of the fan coil unit fault detection model further includes,

[0099] When collecting historical fan speed data and historical operating duration data of the fan coil units in the central air conditioning system, the data is collected periodically, and the collection results are updated to the historical sequence data.

[0100] The updated historical sequence data is preprocessed, and the data format is converted by combining the binary classification label of whether the fan coil unit is faulty, and the sample dataset is updated.

[0101] The updated sample dataset is input into the fan coil unit fault detection model for training, and the detection result of whether the fan coil unit is faulty is output, thus obtaining a new fan coil unit fault detection model.

[0102] The existing fan coil unit fault detection model is replaced with a new one.

[0103] Reference Figure 2 In one embodiment, the following steps are also included:

[0104] S4: Acquire indoor temperature data in the same space as any central air conditioning system, wherein the indoor temperature data is used to reflect the temperature data of the target area of ​​the human body;

[0105] S5: Set the difference between the equipment temperature data of the fan coil unit and the indoor temperature data;

[0106] S61: When the indoor temperature data drops to the same level as the equipment temperature data, control the hot and cold water valves to close;

[0107] S62: When the indoor temperature data rises to the sum of the difference between the device temperature data and the indoor temperature data, the hot and cold water valves are opened.

[0108] In one embodiment, the following steps are also included:

[0109] The real-time temperature data and the early warning information are uploaded to the target monitoring center platform, which is used for centralized remote monitoring and early warning of the fan coil unit failure status of each central air conditioning system.

[0110] The specific descriptions of the above embodiments are as follows.

[0111] Central air conditioning fan coil units are typically installed on the indoor ceiling, making it difficult to detect their malfunctions in a timely manner. Therefore, by utilizing the existing mature product of thermostats and leveraging their IoT functionality, various relevant attribute data of the central air conditioning system's fan coil units can be collected in real time to determine whether the fan coil units are faulty. This eliminates the need for modifications such as installing IoT modules and sensor modules on the fan coil units themselves, representing an indirect method of fan coil unit fault detection at the user's side.

[0112] Specifically, the thermostat is installed at or near the outlet of the fan coil unit. The temperature sensor inside the thermostat is used to monitor the outlet temperature of the fan coil unit, and the temperature sensor transmits the real-time temperature data to the data processing unit.

[0113] Additionally, real-time operating time data and real-time fan speed data of the fan coil unit can be obtained through the fan coil unit's communication interface or switch sensor.

[0114] For example, by recording the on / off command data of the fan coil unit, including the on and off states of the fan coil unit, and recording the timestamps corresponding to the on and off states, the real-time on-time data of the fan coil unit can be determined by subtracting the timestamps corresponding to the on and off states.

[0115] For example, a wind speed sensor can be used to monitor the real-time wind speed during the operation of the fan coil unit, and the real-time wind speed can be compared with a preset range of fan speed settings. If the real-time wind speed is within the low fan speed range, the real-time fan speed data is determined to be low speed data; if the real-time wind speed is within the medium fan speed range, the real-time fan speed data is determined to be medium speed data; if the real-time wind speed is within the high fan speed range, the real-time fan speed data is determined to be high speed data; and so on, the real-time fan speed data is determined.

[0116] The data processing unit receives real-time outlet temperature data of a fan coil unit reported by a thermostat associated with that fan coil unit in any central air conditioning system, as well as real-time fan speed data and real-time operating duration data matched with that fan coil unit in the corresponding central air conditioning system. It then processes and analyzes the data according to a preset algorithm to determine the operating status of the fan coil unit and whether any faults exist, including...

[0117] Determine whether the real-time temperature data is outside the preset temperature threshold range;

[0118] If the real-time temperature data is outside the preset temperature threshold range, the first detection result of the fan coil unit fault is output; if the real-time temperature data is within the preset temperature threshold range, no fault detection result is output; for example, if the real-time temperature data is abnormally high or abnormally low compared to the preset threshold range, it is determined that the fan coil unit may be faulty, and the first detection result of the fan coil unit fault is output.

[0119] Furthermore, the acquired real-time fan speed and corresponding real-time start-up duration data are arranged in the order of acquisition time to obtain the initial sequence data;

[0120] The initial sequence data is preprocessed, such as removing outliers, noise reduction, and data normalization, to obtain preprocessed sequence data. This data is then combined with binary classification labels indicating whether the fan coil unit is faulty to obtain the dataset to be detected.

[0121] Input the dataset to be detected into the preset fan coil unit fault detection model, and output the second detection result of whether the fan coil unit is faulty;

[0122] The system combines the results of the first and second tests to determine whether the fan coil unit is faulty.

[0123] When both the first prediction result and the second detection result indicate a fan coil unit failure, a warning message for the fan coil unit failure will be issued, such as via mobile app, SMS, email, etc., to notify relevant personnel.

[0124] Among them, reference Figure 3 In this embodiment, the specific training process for the machine learning model or deep learning model can be as follows:

[0125] Acquire historical wind turbine speed data and historical start-up duration data within the corresponding preset time period, and arrange them in the order of acquisition time to obtain the initial historical sequence data;

[0126] The initial historical sequence data is preprocessed, such as removing outliers, noise processing, and data normalization, to obtain the target historical sequence data. Combined with the binary classification label of whether the fan coil unit is faulty, the dataset to be trained is obtained.

[0127] The dataset to be trained is input into a machine learning model or a deep learning model for training. The model's output is a second detection result indicating whether the fan coil unit is faulty. In this embodiment, a Transformer model, LSTM model, or similar model can be used for model training.

[0128] Once training is complete, a fan coil unit fault detection model is obtained. Deploying this model allows it to be used for fault detection tasks. This model can use real-time fan start-up data and real-time fan speed data to perform fault detection, identify possible abnormalities or faults in the fan coil unit, and make the detection more intelligent, with better real-time performance and higher detection accuracy.

[0129] Furthermore, the turbine speed data and operating time data can be vectorized, converting them into vector representations in a high-dimensional space. These vector representations are then arranged in chronological order to obtain initial sequence data or initial historical sequence data. This allows the model to understand the characteristics and internal structure of the data, resulting in better training and further improving the model's detection accuracy.

[0130] Furthermore, during the training process, the model's parameters can be continuously adjusted until the difference between the predicted and actual results is minimized, thereby further optimizing the model's detection accuracy.

[0131] In one embodiment, after obtaining the real-time outlet temperature of the fan coil unit, the collected temperature data can be preprocessed first, including removing outliers, noise processing, and data normalization, in order to achieve data cleaning. The preprocessed temperature data will more accurately reflect the actual temperature changes of the fan coil unit, which is conducive to further improving the fault detection accuracy of the fan coil unit.

[0132] For example, temperature data preprocessing can be achieved using statistical analysis, filtering, and other methods to filter out outliers and make the collected temperature data more accurate.

[0133] In one embodiment, the step of determining whether the real-time temperature data of the fan coil unit is abnormal includes:

[0134] Based on the real-time temperature data, a trend curve of the outlet temperature of the fan coil unit is plotted, and it is determined whether the rate of temperature change within a preset time period on the trend curve of the outlet temperature change is outside the preset temperature change value range.

[0135] When the temperature change rate is outside the preset temperature change range, the first detection result of the fan coil unit fault is output.

[0136] By extracting data features, including temperature change rate and temperature change trend curve, from real-time temperature data within a preset time period, the operating status and possible abnormalities of the fan coil unit can be reflected more accurately.

[0137] Within a preset fixed time frame, temperature change data from different time periods are compared horizontally to determine if the fan coil unit is faulty. If the current temperature data shows a significant deviation during the horizontal comparison, it may indicate a fault in the fan coil unit.

[0138] For example, suppose that within a certain time period, the normal temperature variation range of a fan coil unit is set to ±2℃, based on the average outlet temperature of the fan coil unit. For instance, the normal temperature variation range for a fan coil unit would be 20±2℃. If the temperature change rate within a preset time period on a certain day falls outside the preset temperature variation range—for example, if the highest outlet temperature of the fan coil unit reaches 25℃ while the lowest outlet temperature is only 16℃—it indicates that the real-time outlet temperature fluctuation of the fan coil unit during that time period exceeds the normal temperature variation range. Therefore, it can be considered that the outlet temperature data of the fan coil unit on that day has a significant deviation, and the probability of fan coil unit failure is relatively high.

[0139] The working status of the fan coil unit is determined based on the extracted data features. Specific judgment conditions include whether the temperature change rate is within the normal temperature threshold range, whether the temperature change trend is stable, etc., in order to further confirm whether the working status of the fan coil unit is abnormal, so as to make the fault detection results of the fan coil unit more accurate.

[0140] In this embodiment, a threshold can be directly set or a temperature data feature mode can be used to determine whether the fan coil unit is faulty, so as to obtain the first detection result of whether the fan coil unit is faulty, thereby satisfying the balance between detection timeliness and detection accuracy.

[0141] In one embodiment, after comprehensively judging that the fan coil unit has a fault by combining the working status of the fan coil unit and the fault mode identification results of the fan coil unit, corresponding treatment measures can be taken, such as repairing or replacing the faulty parts of the fan coil unit.

[0142] Furthermore, in one embodiment, when collecting historical fan speed data and historical operating time data of the fan coil units in the central air conditioning system in a periodic manner, the collected results are updated to the historical sequence data to continue accumulating historical data and continuously integrating new historical data. With the accumulation of more historical data, the model can learn richer features and patterns, thereby improving the accuracy of prediction or classification; in addition, the model can adapt to changes in data and new trends.

[0143] The updated historical sequence data is preprocessed, and the data format is converted by combining the binary classification label of whether the fan coil unit is faulty, and the sample dataset is updated.

[0144] The updated sample dataset is input into the fan coil unit fault detection model for training, and the detection result of whether the fan coil unit is faulty is output, thus obtaining a new fan coil unit fault detection model.

[0145] A new fan coil unit fault detection model is adopted to replace the existing fan coil unit fault detection model. The fan coil unit fault detection model is retrained periodically, and the model weights are updated, thereby continuously improving the model's accuracy.

[0146] As time progresses, this algorithm repeats the iterative training process described above, continuously integrating newly collected data into the training set and iteratively optimizing the model. By periodically evaluating model performance and adjusting the model based on new data and feedback, the timeliness and accuracy of the model are maintained. This also reduces the impact of data bias.

[0147] In summary, this application obtains real-time temperature data from any thermostat associated with any fan coil unit in any central air conditioning system. This real-time temperature data reflects the real-time outlet temperature of the target fan coil unit, thus determining whether the fan coil unit is faulty. It directly utilizes the existing data acquisition and control command functions of the thermostat to detect fan coil unit faults without requiring modifications to the fan coil unit, reducing the product cost of the central air conditioning system. It also eliminates the need for manual inspections, enabling timely detection of fan coil unit faults and improving detection efficiency. Furthermore, it obtains real-time fan speed data and real-time operating time data of the fan coil unit in the central air conditioning system to obtain initial sequence data. This initial sequence data is preprocessed and combined with the data from the fan coil unit... The system uses binary labels to classify whether a fan coil unit is faulty, converting them into a dataset to be detected. This dataset is then input into a pre-defined fan coil unit fault detection model, which outputs a second detection result indicating whether the fan coil unit is faulty. This leverages a machine learning model to accurately identify fan coil unit faults, achieving intelligent early warning of fan coil unit faults with high detection efficiency and accuracy. Finally, when both the first prediction and second detection results indicate a fan coil unit fault, an early warning message is issued. By comprehensively judging the fault status of the fan coil unit based on the first and second detection results, the system significantly improves the accuracy of fan coil unit fault detection and can detect whether the two-way valve of the ceiling-mounted fan coil unit is faulty.

[0148] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0149] This application embodiment also provides a fan coil unit fault detection system, including any thermostat associated with any fan coil unit installed in any central air conditioning system, the thermostat including a data acquisition unit and a data processing unit;

[0150] The data acquisition unit is used to collect and send the attribute data of the fan coil unit. The attribute data includes the outlet temperature data of the fan coil unit, the fan speed data, and the fan start-up time data.

[0151] The data processing unit receives the attribute data sent by the data acquisition unit, determines whether the real-time outlet temperature of the fan coil unit meets the preset conditions, and outputs a first detection result indicating whether the fan coil unit is faulty; and runs a preset fan coil unit fault detection program to output a second detection result indicating whether the fan coil unit is faulty; when the first prediction result indicates that the fan coil unit is faulty and the second detection result indicates that the fan coil unit is faulty, the fan coil unit is determined to be faulty.

[0152] The fan coil unit fault detection program includes collecting historical fan speed data and historical operating duration data of the fan coil units in the central air conditioning system to obtain historical sequence data; preprocessing the historical sequence data and combining it with binary classification labels indicating whether the fan coil unit is faulty to obtain a sample dataset; inputting the sample dataset into a deep learning model for training, and outputting the detection result of whether the fan coil unit is faulty, until the accuracy of the deep learning model meets the preset requirements, thereby obtaining the fan coil unit fault detection model used to identify whether the fan coil unit is in a fault mode.

[0153] Reference Figure 4 The thermostat includes a data acquisition unit, a data processing unit, and customizable functions.

[0154] The data acquisition unit includes a fan coil temperature sensor and a room temperature sensor. The fan coil temperature sensor is fixedly installed in a suitable location within the central air conditioning system to detect the outlet temperature of the fan coil unit. The room temperature sensor is fixedly installed in a location where users typically move around, such as near indoor light switches, to detect indoor temperature data. It can also reflect the temperature data of target body parts, such as the finger area.

[0155] The data processing unit includes a message middleware, a workflow engine, and a data analysis module. The data analysis module, based on data acquisition, statistical analysis, and data retention functions, uses a preset algorithm to diagnose fan coil unit faults by comparing historical data.

[0156] Customizable features include remote monitoring, fault warnings, and data logging and storage.

[0157] Remote monitoring: By receiving monitoring data and fault information from the data processing unit and sending them to the remote monitoring center, centralized management and remote fault diagnosis can be carried out.

[0158] Fault warning: When a potential fault or abnormality of the fan coil unit is detected, the warning information sent by the data processing unit is sent to relevant personnel so that timely measures can be taken.

[0159] Data recording and storage: Through the data processing unit, historical temperature data and fault information of fan coil units are recorded and stored in the database for easy subsequent analysis and traceability.

[0160] Reference Figure 5 In one embodiment, the functional architecture of the thermostat also includes control and billing functions. The control function includes a temperature module, a working module, and a regulation module.

[0161] The temperature panel can be used to set the temperature of the equipment, calibrate the temperature of the equipment (if the temperature sensor has an error, it can be manually adjusted by adding or subtracting a certain value to correct the temperature display), and set the equipment to stop when a preset temperature threshold is reached.

[0162] The temperature module can also be used for temperature hysteresis. Temperature hysteresis is defined as the difference between the room temperature and the thermostat's set temperature. It reflects the sensitivity of the thermostat's valve output state to room temperature rise / fall, reducing the impact of frequent valve closure on user experience.

[0163] The temperature panel can also be used to set upper and lower temperature limits, and by taking into account the energy-saving management of the equipment, it can meet the needs of users who do not want the temperature to be set too low or too high on site.

[0164] The operating module includes cooling / heating modes and speed settings. Cooling / heating modes include cooling / heating functions, energy-saving functions, ventilation functions, and sleep functions.

[0165] The gear mode allows you to set high, medium, and low fan speeds for the fan coil unit and adjust the control signal of the fan cabinet.

[0166] The control panel includes a power switch, a temperature control button, and a speed control button.

[0167] The billing function includes the design of billing coefficients, tiered billing coefficients, time-based billing coefficients, and time-based billing functions.

[0168] The thermostat's functional architecture also includes a display function, which can be used to visualize time, billing, and temperature control modes, such as countdown, timed tasks, time synchronization, cumulative time, remaining time, outstanding fees, current temperature, fault alarms, cooling / heating / ventilation modes, fan speed, and network connectivity.

[0169] Figure 5 In the blue interface diagram, whether the temperature adjustment and fan speed (high, medium, and low) functions are faulty can be intuitively determined on the panel.

[0170] In this embodiment, the application process of a method for fault detection of fan coil units based on a temperature controller mainly includes:

[0171] Thermostat equipment installation;

[0172] Real-time monitoring and acquisition of target data from target devices;

[0173] Data preprocessing;

[0174] Data analysis;

[0175] Fault diagnosis;

[0176] Troubleshooting.

[0177] Furthermore, this application can also store the collected data in a database for archiving, which is beneficial for subsequent data verification, big data analysis, and so on.

[0178] A method for fault detection of fan coil units based on thermostats is mainly applicable to two-pipe fan coil unit usage scenarios.

[0179] This application also provides a device for fault detection of fan coil units based on a thermostat, which corresponds one-to-one with the method for fault detection of fan coil units based on a thermostat described in the above embodiments. This device for fault detection of fan coil units based on a thermostat includes...

[0180] The coil temperature acquisition module is used to acquire real-time temperature data of any thermostat associated with any fan coil unit in any central air conditioning system. The real-time temperature data is used to reflect the real-time outlet temperature of the fan coil unit.

[0181] The first detection module is used to determine whether the real-time temperature data meets the first preset condition and output the first detection result of whether the fan coil unit is faulty.

[0182] The initial sequence data module is used to obtain the real-time fan speed data and real-time start-up duration data of the fan coil unit in the central air conditioning system to obtain the initial sequence data;

[0183] The dataset to be detected module is used to preprocess the initial sequence data and combine it with the binary classification label of whether the fan coil unit is faulty to obtain the dataset to be detected;

[0184] The second detection module is used to input the dataset to be detected into a preset fan coil unit fault detection model and output a second detection result of whether the fan coil unit is faulty.

[0185] The early warning module is used to issue an early warning message for a fan coil unit failure when both the first prediction result and the second detection result indicate a fan coil unit failure.

[0186] The model module is used to collect historical fan speed data and historical operating time data of the fan coil units in the central air conditioning system to obtain historical sequence data; preprocess the historical sequence data and combine it with binary classification labels indicating whether the fan coil units are faulty to obtain a sample dataset; input the sample dataset into a deep learning model for training, and output the detection results of whether the fan coil units are faulty, until the accuracy of the deep learning model meets the preset requirements, thus obtaining the fan coil unit fault detection model.

[0187] In one embodiment, the model module further includes,

[0188] The historical sequence data update unit is used to collect historical fan speed data and historical start-up duration data of the fan coil units in the central air conditioning system in a periodic manner, and update the collection results to the historical sequence data.

[0189] The sample dataset update unit is used to preprocess the updated historical sequence data and perform data format conversion by combining the binary classification label of whether the fan coil unit is faulty, and update the sample dataset.

[0190] The model iteration unit is used to input the updated sample dataset into the fan coil unit fault detection model for training, and output the detection result of whether the fan coil unit is faulty, thus obtaining a new fan coil unit fault detection model.

[0191] The model replacement unit is used to replace the fan coil unit fault detection model with a new fan coil unit fault detection model.

[0192] In one embodiment, a device for fault detection of fan coil units based on a temperature controller further includes,

[0193] The indoor temperature data module is used to acquire indoor temperature data in the same space as any central air conditioning system. The indoor temperature data is used to reflect the temperature data of the target area of ​​the human body.

[0194] The temperature control hysteresis module is used to set the difference between the equipment temperature data of the fan coil unit and the indoor temperature data.

[0195] The first execution module is used to control the hot and cold water valves to close when the indoor temperature data drops to the same level as the equipment temperature data;

[0196] The second execution module is used to control the hot and cold water valves to open when the indoor temperature data rises to the sum of the difference between the device temperature data and the indoor temperature data.

[0197] By acquiring indoor temperature data from room temperature sensors fixedly installed in locations where users frequently move around, within the same space as any central air conditioning system, the temperature data of target areas of the human body is indirectly reflected. This data is then used to control the opening and closing of the hot and cold water valves of the fan coil units, providing users with a more comfortable temperature environment from the perspective of user perception.

[0198] For specific limitations on a device for fault detection of fan coil units based on a thermostat, please refer to the limitations on a method for fault detection of fan coil units based on a thermostat mentioned above, which will not be repeated here.

[0199] The various modules in the aforementioned device for fault detection of fan coil units based on a temperature controller can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0200] In one embodiment, a computer device is provided, which may be a server. The computer device includes a processor, memory, a network interface, and a database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements any of the above-described methods for fault detection of fan coil units based on a temperature controller.

[0201] In one embodiment, a computer-readable storage medium is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-described methods for fault detection of fan coil units based on a temperature controller.

[0202] In one embodiment, a computer program product is provided, which includes a computer program that, when executed by a processor, implements any of the above-described methods for fault detection of fan coil units based on a temperature controller.

[0203] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. When executed, the computer program may include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0204] Compared with existing technologies, this technical solution has advantages such as real-time monitoring and early warning, low cost, high efficiency, remote monitoring and centralized management, data recording and storage, flexible expansion, and improved user experience.

[0205] It can monitor the operating status and temperature changes of fan coil units in real time, detect potential faults in a timely manner, and notify relevant personnel to take measures through the early warning function, thereby improving the timeliness and effectiveness of fault handling;

[0206] It can utilize existing thermostats and temperature sensors for fan coil unit fault detection, avoiding additional hardware and software costs and reducing maintenance and operating costs. At the same time, by optimizing algorithms and data processing technology, it improves the accuracy and efficiency of fault detection.

[0207] Monitoring data and fault information can be sent to a remote monitoring center to achieve centralized management of fan coil unit fault data and remote fault diagnosis, thereby improving management efficiency and fault handling capabilities.

[0208] It has data recording and storage functions, which can record and store historical temperature data and fault information of fan coil units, facilitating subsequent analysis and tracing, and providing strong support for fault prevention and maintenance;

[0209] It has flexible scalability and can be customized and upgraded according to actual needs to adapt to different types of fan coil unit fault detection, and has good portability and maintainability.

[0210] Real-time monitoring and early warning systems can promptly detect and address fan coil unit malfunctions, reducing inconvenience and frustration for users and improving their user experience.

[0211] This solution utilizes the temperature sensor integrated into the thermostat, enabling accurate detection of the fan coil unit's operating status without any additional modifications.

[0212] This solution, designed from the user's perspective, monitors the outlet temperature of the fan coil unit and the perceived temperature in real time. When the room temperature sensor detects an abnormal temperature change, the system reacts quickly, issuing an alert and reminding relevant personnel to open or close the hot and cold water valves of the fan coil unit. This rapid response mechanism avoids energy waste and safety hazards caused by equipment failure, providing users with a more comfortable and safer indoor environment. These room temperature sensors are installed in locations close to areas where people normally move around, thus more accurately reflecting people's temperature perception. This innovation not only improves detection accuracy but also significantly increases detection efficiency.

[0213] Furthermore, this solution is highly scalable and sustainable. With continuous technological advancements and changes in market demands, it can be further integrated with other sensors and intelligent control modules to achieve more comprehensive and intelligent fault monitoring and management of central air conditioning system fan coil units. This provides users with more choices and flexibility, while also opening up new possibilities for future technological development.

[0214] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A method for fault detection of fan coil units based on a thermostat, characterized in that, Includes the following steps, Obtain real-time temperature data of any thermostat associated with any fan coil unit in any central air conditioning system, wherein the real-time temperature data is used to reflect the real-time outlet temperature of the fan coil unit. Determine whether the real-time temperature data meets preset conditions, and output the first detection result of whether the fan coil unit is faulty; And obtain the real-time fan speed data and real-time start-up duration data of the fan coil unit in the central air conditioning system to obtain the initial sequence data; The initial sequence data is preprocessed and combined with binary classification labels indicating whether the fan coil unit is faulty to obtain the dataset to be detected. Input the dataset to be detected into the preset fan coil unit fault detection model, and output a second detection result of whether the fan coil unit is faulty; When both the first and second detection results indicate a fan coil unit malfunction, a warning message for a fan coil unit malfunction is issued. The training steps for the fan coil unit fault detection model include: Collect historical fan speed data and historical start-up duration data of the fan coil units in the central air conditioning system to obtain historical sequence data; The historical sequence data is preprocessed and combined with binary classification labels indicating whether the fan coil unit is faulty to obtain a sample dataset. The sample dataset is input into a deep learning model for training, and the detection result of whether the fan coil unit is faulty is output until the accuracy of the deep learning model meets the preset requirements, thus obtaining the fan coil unit fault detection model.

2. The method for fault detection of fan coil units based on a temperature controller according to claim 1, characterized in that, The steps for determining whether the real-time temperature data meets preset conditions and outputting a first detection result indicating whether the fan coil unit is faulty include: When the real-time temperature data is outside the preset temperature threshold range, the first detection result of the fan coil unit fault is output. Alternatively, a trend curve of the outlet temperature of the fan coil unit can be plotted based on the real-time temperature data, and it can be determined whether the rate of temperature change within a preset time period on the trend curve is outside the preset temperature change range. When the rate of temperature change is outside the preset temperature change range, the first detection result of the fan coil unit fault can be output.

3. The method for fault detection of fan coil units based on a temperature controller according to claim 1, characterized in that, The training steps for the fan coil unit fault detection model also include, When collecting historical fan speed data and historical operating duration data of the fan coil units in the central air conditioning system, the data is collected periodically, and the collection results are updated to the historical sequence data. The updated historical sequence data is preprocessed, and the data format is converted by combining the binary classification label of whether the fan coil unit is faulty, and the sample dataset is updated. The updated sample dataset is input into the fan coil unit fault detection model for training, and the detection result of whether the fan coil unit is faulty is output, thus obtaining a new fan coil unit fault detection model. The existing fan coil unit fault detection model is replaced with a new one.

4. The method for fault detection of fan coil units based on a temperature controller according to claim 1, characterized in that, It also includes the following steps, Acquire indoor temperature data in the same space as any central air conditioning system, wherein the indoor temperature data is used to reflect the temperature data of a target area of ​​the human body; Set the difference between the equipment temperature data of the fan coil unit and the indoor temperature data; When the indoor temperature drops to the same level as the equipment temperature, the hot and cold water valves are shut off. When the indoor temperature rises to the sum of the difference between the device temperature and the indoor temperature, the hot and cold water valves are opened.

5. The method for fault detection of fan coil units based on a temperature controller according to any one of claims 1-4, characterized in that, It also includes the following steps, The real-time temperature data and the early warning information are uploaded to the target monitoring center platform, which is used for centralized remote monitoring and early warning of the fan coil unit failure status of each central air conditioning system.

6. A device for fault detection of fan coil units based on a temperature controller, characterized in that, include, The coil temperature acquisition module is used to acquire real-time temperature data of any thermostat associated with any fan coil unit in any central air conditioning system. The real-time temperature data is used to reflect the real-time outlet temperature of the fan coil unit. The first detection module is used to determine whether the real-time temperature data meets the first preset condition and output the first detection result of whether the fan coil unit is faulty. The initial sequence data module is used to obtain the real-time fan speed data and real-time start-up duration data of the fan coil unit in the central air conditioning system to obtain the initial sequence data; The dataset to be detected module is used to preprocess the initial sequence data and combine it with the binary classification label of whether the fan coil unit is faulty to obtain the dataset to be detected; The second detection module is used to input the dataset to be detected into a preset fan coil unit fault detection model and output a second detection result of whether the fan coil unit is faulty. The early warning module is used to issue an early warning message for a fan coil unit failure when both the first detection result and the second detection result indicate a fan coil unit failure. The model module is used to collect historical fan speed data and historical operating time data of the fan coil units in the central air conditioning system to obtain historical sequence data; preprocess the historical sequence data and combine it with binary classification labels indicating whether the fan coil units are faulty to obtain a sample dataset; input the sample dataset into a deep learning model for training, and output the detection results of whether the fan coil units are faulty, until the accuracy of the deep learning model meets the preset requirements, thus obtaining the fan coil unit fault detection model.

7. The device for fault detection of fan coil units based on a temperature controller according to claim 6, characterized in that, The model module also includes, The historical sequence data update unit is used to collect historical fan speed data and historical start-up duration data of the fan coil units in the central air conditioning system in a periodic manner, and update the collection results to the historical sequence data. The sample dataset update unit is used to preprocess the updated historical sequence data and perform data format conversion by combining the binary classification label of whether the fan coil unit is faulty, and update the sample dataset. The model iteration unit is used to input the updated sample dataset into the fan coil unit fault detection model for training, and output the detection result of whether the fan coil unit is faulty, thus obtaining a new fan coil unit fault detection model. The model replacement unit is used to replace the fan coil unit fault detection model with a new fan coil unit fault detection model.

8. The device for fault detection of fan coil units based on a temperature controller according to claim 6, characterized in that, It also includes, The indoor temperature data module is used to acquire indoor temperature data in the same space as any central air conditioning system. The indoor temperature data is used to reflect the temperature data of the target area of ​​the human body. The temperature control hysteresis module is used to set the difference between the equipment temperature data of the fan coil unit and the indoor temperature data. The first execution module is used to control the hot and cold water valves to close when the indoor temperature data drops to the same level as the equipment temperature data; The second execution module is used to control the hot and cold water valves to open when the indoor temperature data rises to the sum of the difference between the device temperature data and the indoor temperature data.

9. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

10. A fan coil unit fault detection system, characterized in that, Includes any thermostat installed in any central air conditioning system and associated with any fan coil unit, the thermostat including a data acquisition unit and a data processing unit; The data acquisition unit is used to collect and send the attribute data of the fan coil unit. The attribute data includes the outlet temperature data of the fan coil unit, the fan speed data, and the fan start-up time data. The data processing unit receives the attribute data sent by the data acquisition unit, determines whether the real-time outlet temperature of the fan coil unit meets the preset conditions, and outputs the first detection result of whether the fan coil unit is faulty. And run the preset fan coil unit fault detection program and output the second detection result of whether the fan coil unit is faulty; When both the first and second detection results indicate a fan coil unit failure, the fan coil unit is determined to be faulty. The fan coil unit fault detection program includes collecting historical fan speed data and historical operating duration data of the fan coil units in the central air conditioning system to obtain historical sequence data; preprocessing the historical sequence data and combining it with binary classification labels indicating whether the fan coil unit is faulty to obtain a sample dataset; inputting the sample dataset into a deep learning model for training, and outputting the detection result of whether the fan coil unit is faulty, until the accuracy of the deep learning model meets the preset requirements, thereby obtaining the fan coil unit fault detection model used to identify whether the fan coil unit is in a fault mode.

Images