Dehumidifier fault detection method, system, electronic device and storage medium

Abstract

A dehumidifier fault detection method, system, electronic device and storage medium, relating to the technical field of dehumidifier fault detection. The method comprises: obtaining the current dehumidification mode and multi-dimensional indicator data of the dehumidifier; performing abnormality detection based on the dehumidification mode and the multi-dimensional indicator data to obtain an abnormality detection result; when the abnormality detection result is that the dehumidifier is operating abnormally, obtaining the vibration data of each preset component in the dehumidifier, the pressure data of the refrigeration pipe and the speed data of the fan; performing time domain and frequency domain analysis on the vibration data of each preset component to obtain a vibration feature set of each preset component; locating the fault based on each vibration feature set, the pressure data and the speed data, and generating a fault detection report for the dehumidifier. The implementation of the technical solution provided in the present application can timely and accurately detect the fault condition of the dehumidifier, thereby reducing further damage or maintenance costs of the dehumidifier.

Description

Technical Field

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

[0002] Dehumidifiers are widely used to control air humidity to provide a more comfortable environment or to meet specific process requirements. The performance of dehumidifiers directly affects air quality and energy efficiency. Therefore, it is crucial to maintain their stable and efficient operation.

[0003] At present, traditional dehumidifier fault detection methods usually use basic sensors to monitor key parameters of the device, such as temperature, humidity, and power consumption. These parameters help to determine whether the device is working properly. However, these methods mainly rely on simple threshold comparisons. For example, if the temperature or humidity exceeds the preset range, it may indicate that the device has a serious fault. However, this fault detection method often cannot detect the fault of the dehumidifier in a timely and accurate manner, resulting in increased damage to the dehumidifier or higher maintenance costs. Summary of the invention

[0004] The present application provides a dehumidifier fault detection method, system, electronic device and storage medium, which can timely and accurately detect the fault of the dehumidifier, thereby reducing further damage or maintenance costs of the dehumidifier.

[0005] In a first aspect, the present application provides a dehumidifier fault detection method, the method comprising:

[0006] Obtaining the current dehumidification mode and multi-dimensional indicator data of the dehumidifier, wherein the multi-dimensional indicator data includes first temperature and humidity data of the air inlet of the dehumidifier, second temperature and humidity data of the air outlet, refrigeration pipe surface temperature data, and power data;

[0007] Performing anomaly detection based on the dehumidification mode and the multi-dimensional indicator data to obtain an anomaly detection result;

[0008] When the abnormality detection result is that the dehumidifier is operating abnormally, obtaining vibration data of each preset component in the dehumidifier, pressure data of the refrigeration pipe, and speed data of the fan;

[0009] Performing time domain and frequency domain analysis on the vibration data of each of the preset components to obtain a vibration feature set of each of the preset components;

[0010] Fault location is performed based on each of the vibration feature sets, the pressure data, and the rotational speed data, and a fault detection report of the dehumidifier is generated.

[0011] By adopting the above technical solution, the current dehumidification mode of the dehumidifier and multi-dimensional indicator data including inlet and outlet temperature and humidity data, refrigeration pipe surface temperature data and power data are obtained to achieve comprehensive monitoring of the dehumidifier operation status; secondly, based on the dehumidification mode and multi-dimensional indicator data, abnormality detection can be performed to timely detect abnormal operation of the dehumidifier; when abnormal operation of the dehumidifier is detected, the vibration data, refrigeration pipe pressure data and fan speed data of each preset component are further obtained, and the vibration feature set is obtained by performing time domain and frequency domain analysis on the vibration data, and the pressure data and speed data are combined to locate the fault, thereby achieving accurate positioning of the fault. This multi-level and multi-dimensional fault detection method not only overcomes the technical problems of untimely and inaccurate detection caused by relying only on simple threshold comparison in the prior art, but also can detect abnormalities at the early stage of the fault and accurately locate the faulty component, effectively reducing the risk of further damage to the dehumidifier and reducing maintenance costs.

[0012] In a second aspect of the present application, a fault detection system for a dehumidifier is provided, the system comprising:

[0013] A first data acquisition module is used to acquire the current dehumidification mode and multi-dimensional index data of the dehumidifier, wherein the multi-dimensional index data includes first temperature and humidity data of the air inlet of the dehumidifier, second temperature and humidity data of the air outlet, refrigeration pipe surface temperature data, and power data;

[0014] An anomaly detection module, used to perform anomaly detection based on the dehumidification mode and the multi-dimensional indicator data to obtain an anomaly detection result;

[0015] The second data acquisition module is further used to acquire vibration data of each preset component in the dehumidifier, pressure data of the refrigeration pipe and speed data of the fan when the abnormality detection result is that the dehumidifier is operating abnormally;

[0016] A vibration data analysis module, used to perform time domain and frequency domain analysis on the vibration data of each of the preset components to obtain a vibration feature set of each of the preset components;

[0017] A fault report generating module is used to locate the fault based on each of the vibration feature sets, the pressure data and the rotation speed data, and to generate a fault detection report for the dehumidifier.

[0018] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0019] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0020] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0021] This application achieves comprehensive monitoring of the dehumidifier's operating status by obtaining the dehumidifier's current dehumidification mode and multi-dimensional indicator data including inlet and outlet temperature and humidity data, refrigeration pipe surface temperature data, and power data; secondly, based on the dehumidification mode and multi-dimensional indicator data, abnormality detection is performed to timely detect abnormal operation of the dehumidifier; when abnormal operation of the dehumidifier is detected, the vibration data, refrigeration pipe pressure data, and fan speed data of each preset component are further obtained, and the vibration feature set is obtained by performing time domain and frequency domain analysis on the vibration data, and the pressure data and speed data are combined to locate the fault, thereby achieving accurate positioning of the fault. This multi-level and multi-dimensional fault detection method not only overcomes the technical problems of untimely and inaccurate detection caused by relying only on simple threshold comparison in the prior art, but also can detect abnormalities at the early stage of the fault and accurately locate the faulty component, effectively reducing the risk of further damage to the dehumidifier and reducing maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of a fault detection method for a dehumidifier provided in an embodiment of the present application;

[0023] Figure 2 It is a module schematic diagram of a fault detection system for a dehumidifier provided in an embodiment of the present application;

[0024] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0025] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0026] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0028] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0030] Please refer to Figure 1 , a flow chart of a dehumidifier fault detection method is proposed, the method can be implemented by a computer program, can be implemented by a single-chip microcomputer, and can also be run on a dehumidifier fault detection system, the computer program can be integrated in a computer device, and can also be run as an independent tool application. Specifically, the method includes steps 10 to 50, and the above steps are as follows:

[0031] Step 10: Obtain the current dehumidification mode and multi-dimensional indicator data of the dehumidifier, the multi-dimensional indicator data including the first temperature and humidity data of the dehumidifier air inlet, the second temperature and humidity data of the air outlet, the refrigeration pipe surface temperature data and the power data.

[0032] In the embodiment of the present application, the dehumidification mode refers to the operating condition of the dehumidifier, specifically including but not limited to: continuous dehumidification mode, intelligent dehumidification mode and timed dehumidification mode, wherein the continuous dehumidification mode means that the dehumidifier runs continuously to maintain the set target humidity, the intelligent dehumidification mode means automatically adjusting the dehumidification amount according to the ambient humidity, and the timed dehumidification mode means performing dehumidification operations within a preset time period.

[0033] In the embodiment of the present application, multi-dimensional index data refers to multiple key parameters that reflect the operating status of the dehumidifier, including: the first temperature and humidity data of the air inlet is used to characterize the inlet air state, the second temperature and humidity data of the air outlet is used to characterize the outlet air state, the refrigeration pipe surface temperature data is used to reflect the heat exchange effect of the refrigeration system, and the power data is used to reflect the energy consumption of the dehumidifier. These data together constitute the basic data set for evaluating the operating status of the dehumidifier. By simultaneously monitoring these different dimensions of index data, the working status and performance of the dehumidifier can be fully reflected.

[0034] Specifically, the currently set dehumidification mode is read through the control unit of the dehumidifier. The dehumidification mode includes continuous dehumidification mode, intelligent dehumidification mode and timed dehumidification mode. There are differences in the operating characteristics and normal parameter range of the dehumidifier under different dehumidification modes. Therefore, obtaining the dehumidification mode helps to accurately judge the operating status of the dehumidifier. Secondly, temperature and humidity sensors are respectively set at the air inlet and outlet of the dehumidifier. The temperature and humidity sensors collect temperature and humidity data every preset time interval (for example, 1 minute), wherein the first temperature and humidity data of the air inlet is used to characterize the temperature and humidity state of the inlet air, and the second temperature and humidity data of the air outlet is used to characterize the temperature and humidity state of the outlet air. The dehumidification effect of the dehumidifier can be evaluated by comparing the temperature and humidity difference between the inlet and outlet. At the same time, multiple temperature sensors are set on the surface of the refrigeration pipe. These temperature sensors are evenly distributed along the length direction of the refrigeration pipe, and are used to collect the surface temperature data of the refrigeration pipe. The surface temperature data of the refrigeration pipe reflects the heat exchange effect and working status of the refrigeration system. In addition, the power data of the dehumidifier is collected in real time. The power data can include the power of the whole machine and the sub-item power of the main electrical components (such as compressors and fans), which are used to monitor the energy consumption and operating status of the dehumidifier. All collected data are preprocessed and stored, including data smoothing, outlier filtering and data standardization, to improve the accuracy of subsequent analysis. This multi-dimensional data collection solution can not only fully monitor the operating status of the dehumidifier, but also provide reliable data support for subsequent anomaly detection, thereby improving the accuracy and timeliness of fault detection.

[0035] Based on the above embodiment, as an optional embodiment, the step of obtaining the current dehumidification mode and multi-dimensional indicator data of the dehumidifier may further include the following steps:

[0036] Step 101: obtaining the operating parameters and environmental parameters set by the user, the operating parameters including the target humidity and the wind speed level, and the environmental parameters including the indoor temperature and relative humidity.

[0037] Specifically, the control panel collects the operating parameters input by the user through buttons or touch, and the operating parameters include target humidity and wind speed gear, where the setting range of target humidity is 35%RH to 80%RH, and the wind speed gear is divided into three gears: low speed, medium speed and high speed. At the same time, the temperature and humidity sensor set in the room collects environmental parameters, including indoor temperature and relative humidity. The temperature and humidity sensor collects data every preset time (for example, 30 seconds) and transmits it to the control unit.

[0038] Step 102: Determine the current dehumidification mode of the dehumidifier according to the operating parameters and environmental parameters.

[0039] Specifically, after receiving the operating parameters and environmental parameters, the control unit first determines the difference between the target humidity and the current indoor relative humidity. When the difference is greater than a preset threshold (e.g., 20%RH), it automatically switches to continuous dehumidification mode to quickly reduce the indoor humidity. When the difference is within a preset range (e.g., 5%RH to 20%RH), the intelligent dehumidification mode is selected according to the setting of the wind speed gear. In this mode, the control unit dynamically adjusts the dehumidification amount according to the changing trend of the indoor temperature and relative humidity. When the difference is less than another preset threshold (e.g., 5%RH), it switches to timed dehumidification mode. In this mode, the dehumidifier runs at a preset time interval to maintain the stability of the indoor humidity. This automatic selection scheme of dehumidification mode based on operating parameters and environmental parameters can not only adapt to different usage requirements and environmental conditions, but also improve dehumidification efficiency and energy utilization through intelligent switching of modes.

[0040] Step 103: Determine the corresponding data sampling frequency and sampling duration according to the dehumidification mode.

[0041] Specifically, the control unit adaptively adjusts the data sampling strategy according to the determined dehumidification mode. In the continuous dehumidification mode, since the dehumidifier continues to run at a high load, more frequent monitoring of the operating status is required. Therefore, the data sampling frequency is set to a higher level (for example, sampling once every 30 seconds), and the sampling duration is set to continuous sampling; in the intelligent dehumidification mode, considering the dynamic changes in the dehumidifier load, the data sampling frequency is set to a medium level (for example, sampling once every 1 minute), and the sampling duration is set to each operating cycle; in the timed dehumidification mode, since the operating load is relatively stable, the data sampling frequency is set to a lower level (for example, sampling once every 2 minutes), and the sampling duration is set to the operating period.

[0042] Step 104: Collect multi-dimensional indicator data according to the data sampling frequency and sampling duration.

[0043] Specifically, according to the data sampling frequency and sampling duration, the first temperature and humidity data of the air inlet and the second temperature and humidity data of the air outlet are collected through the temperature and humidity sensor; the surface temperature data of the refrigeration pipe is collected through the surface temperature sensor, and the surface temperature sensor is evenly distributed along the refrigeration pipe at a preset interval (for example, 10 cm); the power sensor is used to collect the power data of the whole machine and the sub-item power data of key components such as the compressor and the fan. The collected data is preprocessed by the data acquisition module, including removing outliers, data smoothing and standardization. The preprocessed data is stored in the data cache according to the timestamp and is updated and stored regularly. This adaptive sampling scheme based on the dehumidification mode not only ensures the timeliness and integrity of data collection, but also avoids the storage and processing burden brought by redundant data collection. At the same time, the differentiated sampling strategies under different modes can better reflect the operating characteristics of the dehumidifier under various working conditions.

[0044] Step 20: Perform anomaly detection based on the dehumidification mode and multi-dimensional indicator data to obtain anomaly detection results.

[0045] Specifically, first determine the corresponding standard index range according to the dehumidification mode, that is, the threshold or standard range corresponding to each index. First, analyze the first temperature and humidity data of the air inlet and the second temperature and humidity data of the air outlet, and calculate the temperature and humidity difference. When the temperature and humidity difference of three consecutive sampling cycles is less than the preset threshold (for example, the temperature difference is less than 5°C or the humidity difference is less than 10%RH), it is determined that the dehumidification effect is abnormal. Secondly, analyze the surface temperature data of the refrigeration pipe. When the temperature of any measuring point exceeds the normal working range (for example, 0°C to 15°C) or the temperature difference of adjacent measuring points exceeds the preset value (for example, 8°C), it is determined to be abnormal heat exchange. Then, analyze the power data. When the power of the whole machine or the power of any key component exceeds the preset range (for example, the power fluctuation of the compressor exceeds 20% of the rated power), or the power change trend is abnormal (for example, the power continues to rise by more than 30% within 30 minutes), it is determined to be power abnormal. When there is any abnormality, it is determined that the abnormal detection result is that the dehumidifier is operating abnormally. The embodiment of the present application also establishes an abnormal pattern recognition mechanism based on time series, and identifies potential abnormal signs by analyzing the data change trend in the last 24 hours. For example, when the outlet temperature shows a slow but continuous upward trend within 4 hours, and the increase exceeds 3°C, the system will warn of possible refrigeration system abnormalities in advance. At the same time, the system will also comprehensively analyze the correlation between multiple indicators. For example, when the compressor power increases but the dehumidification effect does not improve significantly, it may indicate problems such as refrigerant leakage or system blockage.

[0046] Based on the above embodiment, as an optional embodiment, the step of performing anomaly detection based on the dehumidification mode and the multi-dimensional indicator data to obtain anomaly detection results may also include the following steps:

[0047] Step 201: Calculate a ratio sequence of first temperature and humidity data and corresponding second temperature and humidity data, and calculate the energy efficiency ratio of the dehumidifier based on the power data.

[0048] Specifically, the collected temperature and humidity data are first time-aligned, and the first temperature and humidity data of the air inlet and the second temperature and humidity data of the air outlet collected at the same time are paired. In order to ensure the accuracy of the calculation, the system uses the sliding window method to pre-process the data. For example, the window length is set to 10 minutes, and the temperature and humidity data in the window are averaged to eliminate the influence of instantaneous fluctuations. For the data in each time window, the temperature ratio (second temperature / first temperature) and humidity ratio (second humidity / first humidity) are calculated respectively, so as to obtain a ratio sequence reflecting the temperature and humidity change characteristics of the dehumidification process.

[0049] At the same time, the system calculates the energy efficiency ratio of the dehumidifier based on the power data, which is specifically characterized by the ratio of dehumidification capacity to power consumption. First, the dehumidification capacity per unit time is calculated based on the humidity difference between the inlet and outlet and the air volume data, where the air volume is obtained by looking up the table according to the wind speed gear, for example, the low speed gear is 200m³ / h, the medium speed gear is 300m³ / h, and the high speed gear is 400m³ / h. Then, the calculated dehumidification capacity is divided by the average power of the corresponding period to obtain the energy efficiency ratio value. The system calculates the energy efficiency ratio every 30 minutes and records the trend of the energy efficiency ratio changes in the last 24 hours.

[0050] Step 202: Determine the corresponding standard index range according to the dehumidification mode, the standard index range includes the temperature and humidity ratio range of the air inlet and the air outlet, the surface temperature range of the refrigeration pipe, and the energy efficiency ratio range.

[0051] Specifically, the control unit sets a corresponding standard index range according to the dehumidification mode of the dehumidifier. For the continuous dehumidification mode, since the dehumidifier is in a high-load operation state, the temperature ratio range of the inlet and outlet is set to 0.75 to 0.85, the humidity ratio range is set to 0.45 to 0.55, the refrigeration pipe surface temperature range is set to 2°C to 8°C, and the energy efficiency ratio range is set to 2.0 to 2.5 liters / kWh; for the intelligent dehumidification mode, taking into account the dynamic change characteristics of the operating load, the temperature ratio range is set to 0.80 to 0.90, the humidity ratio range is set to 0.50 to 0.65, the refrigeration pipe surface temperature range is set to 5°C to 12°C, and the energy efficiency ratio range is set to 1.8 to 2.2 liters / kWh; for the timed dehumidification mode, since the operating load is relatively light, the temperature ratio range is set to 0.85 to 0.95, the humidity ratio range is set to 0.60 to 0.75, the refrigeration pipe surface temperature range is set to 8°C to 15°C, and the energy efficiency ratio range is set to 1.5 to 2.0 liters / kWh.

[0052] Step 203: When any ratio in the ratio sequence exceeds the temperature and humidity ratio range, and / or the refrigeration pipe surface temperature data exceeds the refrigeration pipe surface temperature range, and / or the energy efficiency ratio exceeds the energy efficiency ratio range, the abnormal detection result is determined to be abnormal dehumidifier operation.

[0053] Specifically, the sliding window method is used to monitor the continuously collected data in real time, and the window length is set to 15 minutes. When it is detected that the temperature ratio or humidity ratio exceeds the standard range of the corresponding mode for three consecutive sampling cycles, and / or when the surface temperature of the refrigeration pipe at any measuring point exceeds the standard range for two consecutive sampling cycles, or the temperature difference between adjacent measuring points exceeds 6°C, and / or when the energy efficiency ratio is lower than the standard range for four consecutive sampling cycles, the abnormal detection result is determined to be abnormal operation of the dehumidifier.

[0054] Step 30: When the abnormality detection result is that the dehumidifier is operating abnormally, the vibration data of each preset component in the dehumidifier, the pressure data of the refrigeration pipe, and the speed data of the fan are obtained.

[0055] Specifically, when the control unit determines that the dehumidifier is operating abnormally, the fault diagnosis process is immediately started. The preset components include the compressor, evaporator, condenser, refrigeration pipe and fan. In order to accurately locate the cause of the fault, the system needs to obtain the operating status data of these key components. Vibration data is collected by vibration sensors installed on the surface of each preset component. The sampling frequency of the vibration sensor is set to 1000Hz, and each collection lasts for 10 seconds. The vibration data reflects the mechanical operating status of each component, including vibration frequency and vibration amplitude, which can be used to determine whether there are mechanical faults such as looseness, wear or failure of the component. For example, abnormal vibration of the compressor may indicate mechanical wear or loose components, and abnormal vibration of the evaporator and condenser may indicate frost or dust accumulation problems.

[0056] Pressure data is collected through pressure sensors installed at the inlet, middle and outlet of the refrigeration pipe. The sampling frequency is set to 1Hz and the data is collected continuously for 5 minutes. The pressure data reflects the working status of the refrigeration system and can be used to determine whether the refrigerant cycle is normal and whether there is leakage or blockage. The inlet pressure reflects the compressor outlet status, the outlet pressure reflects the expansion valve working status, and the pressure distribution reflects the refrigerant flow status. At the same time, the speed data of the fan is collected in real time through the Hall sensor. The sampling frequency is set to 10Hz and the data is collected continuously for 2 minutes. The speed data reflects the actual operating status of the fan and can be used to determine whether the air supply system is working normally and whether the fan motor has performance degradation. The system records the actual speed value of the fan at the current operating gear and monitors the stability of the speed. By obtaining the two key data of the pressure data of the refrigeration pipe and the speed data of the fan, combined with the vibration data of each preset component, the system can more comprehensively and accurately evaluate the operating status of the dehumidifier, improve the accuracy of fault diagnosis and maintenance efficiency.

[0057] Step 40: Perform time domain and frequency domain analysis on the vibration data of each preset component to obtain a vibration feature set of each preset component.

[0058] Specifically, the time domain-frequency domain dual analysis method is used to process the collected vibration data of the preset components to obtain comprehensive vibration characteristic information. First, in terms of time domain analysis, the system calculates the statistical characteristics of the vibration signal, such as the root mean square value, peak factor, waveform factor, and peak-to-peak value. By segmenting the 30-second sampling data, taking 4096 data points in each segment, the mean and standard deviation of the time domain characteristic values ​​are calculated to form a time domain characteristic vector. These time domain characteristics can reflect the intensity and waveform characteristics of the vibration. For example, an abnormal increase in the peak factor usually indicates an impact failure in the equipment, and a change in the waveform factor reflects the degree of waveform distortion of the vibration signal.

[0059] Then the system performs frequency domain analysis on the vibration data and converts the time domain signal into a spectrum using fast Fourier transform (FFT). To improve the accuracy of spectrum analysis, the system first performs windowing on the original signal and selects the Hanning window to reduce spectrum leakage. In frequency domain feature extraction, the system calculates the center frequency, mean square frequency, band energy distribution and amplitude of the main harmonic components of the spectrum. At the same time, the envelope demodulation technology is used to analyze the modulation characteristics, and the envelope spectrum of the vibration signal is extracted by Hilbert transform to detect periodic impact characteristics. These frequency domain features can reflect the fault characteristic frequency of the equipment. For example, a compressor bearing fault will produce a characteristic spectrum line at a specific frequency, and a transmission component fault will cause sideband modulation. The extracted time domain features and frequency domain features are combined to form a vibration feature set, including but not limited to: time domain statistical feature vector (root mean square value, peak factor, waveform factor, peak-to-peak value), frequency domain basic features (center frequency, mean square frequency, band energy ratio), harmonic features (fundamental frequency amplitude, harmonic ratio) and modulation features (sideband intensity, modulation depth), etc.

[0060] Based on the above embodiment, as another optional embodiment, the step of performing time domain and frequency domain analysis on the vibration data of each preset component to obtain the vibration feature set of each preset component may also include the following steps:

[0061] Step 401: performing wavelet denoising processing on the vibration data of each preset component to obtain denoised vibration data.

[0062] Specifically, considering that factors such as environmental noise and electromagnetic interference during the operation of the dehumidifier will affect the quality of the vibration signal, the collected vibration data of the preset components are first subjected to wavelet denoising. The system uses the db4 wavelet basis function to perform a 5-layer wavelet decomposition on the original vibration signal to obtain wavelet coefficients in different frequency bands. The wavelet coefficients are processed by the soft threshold method, in which the threshold selection is adaptively determined using the empirical Bayes method to suppress noise to the greatest extent while retaining the effective signal. Then, the system reconstructs the processed wavelet coefficients to obtain the denoised vibration data. This wavelet denoising method can effectively maintain the mutation characteristics and transient information of the signal, while significantly improving the signal-to-noise ratio of the signal.

[0063] Step 402: Calculate the root mean square value, peak factor, waveform factor, and pulse factor of the noise-reduced vibration data to obtain time domain features.

[0064] Specifically, the time domain statistical characteristics of the vibration data after noise reduction are calculated. First, the root mean square value is calculated. This value reflects the energy level of the vibration signal. It is obtained by calculating the mean of the sum of squares of all sampling points and then taking the square root. An increase in the root mean square value usually indicates that the overall vibration intensity of the equipment has increased, and there may be a fault. Then the peak factor is calculated, that is, the ratio of the maximum peak value to the root mean square value. This feature is particularly sensitive to early faults. When the equipment has an initial fault, the peak factor will increase significantly. Then the waveform factor is calculated, that is, the ratio of the root mean square value to the average amplitude. This feature can reflect the degree of waveform distortion. When the equipment fails, the waveform will be distorted, resulting in a change in the waveform factor. Finally, the pulse factor is calculated, that is, the ratio of the maximum peak value to the average amplitude. This feature is particularly sensitive to impact-type faults. When the equipment is severely impacted, the pulse factor will increase significantly.

[0065] By adopting the above technical solutions, wavelet denoising can analyze signals at different scales, has a good processing effect on non-stationary signals, and can effectively remove background noise while retaining fault characteristics; secondly, the four time domain statistical characteristics have their own characteristics and can reflect the operating status of the equipment from different angles. For example, the root mean square value reflects the overall vibration level, the peak factor and pulse factor are sensitive to early faults and impact faults, and the waveform factor can reflect the degree of signal distortion.

[0066] Step 403: Perform fast Fourier transform on the noise-reduced vibration data to extract spectrum features.

[0067] Specifically, in order to fully obtain the vibration characteristic information of the preset components, the vibration data after noise reduction is analyzed in the frequency domain. The system uses fast Fourier transform (FFT) to convert the time domain signal to the frequency domain. Before performing FFT, the signal is windowed and the Hanning window is selected to reduce the spectrum leakage effect. The amplitude spectrum of the vibration signal obtained by FFT reflects the energy distribution of the signal at different frequency components.

[0068] Step 404: Calculate the centroid frequency, mean square frequency, and frequency band energy distribution of the frequency spectrum features to obtain frequency domain features.

[0069] Specifically, after obtaining the spectrum characteristics, the system calculates three key frequency domain characteristic parameters. First, the center of gravity frequency is calculated, that is, the frequency is used as the weight to calculate the weighted average of the spectrum. The center of gravity frequency reflects the concentration of the spectrum distribution of the vibration signal. When the equipment fails, the energy distribution of the spectrum will change, causing the center of gravity frequency to shift. Then the mean square frequency is calculated, that is, the weighted average of the square of the frequency. This feature is more sensitive to high-frequency components and can reflect the high-frequency vibration characteristics of the equipment. Finally, the frequency band energy distribution is calculated. The system divides the spectrum into three frequency bands: low frequency band (0-200Hz), medium frequency band (200-800Hz) and high frequency band (above 800Hz). The proportion of energy in each frequency band to the total energy is calculated. Changes in these energy proportions can reflect the type and severity of the fault.

[0070] Step 405: combining the time domain features and frequency domain features corresponding to each preset component to obtain a vibration feature set of each preset component.

[0071] Specifically, the obtained time domain features (RMS value, peak factor, waveform factor and pulse factor) are combined with the frequency domain features (center frequency, mean square frequency and frequency band energy distribution) to form a vibration feature set for each preset component. For example, for a compressor, its feature set includes the RMS value reflecting the overall vibration intensity, the peak factor and pulse factor reflecting the impact characteristics, the center frequency and mean square frequency reflecting the frequency distribution, and the frequency band energy ratio reflecting the energy distribution characteristics. This combination of multi-dimensional features can fully describe the vibration state of the equipment and provide rich feature information for subsequent fault diagnosis.

[0072] Step 50: Fault location is performed based on each vibration feature set, pressure data, and rotation speed data, and a fault detection report of the dehumidifier is generated.

[0073] Specifically, fault location analysis is performed based on the multi-source data fusion method, and the vibration feature set of each preset component, the pressure data of the refrigeration pipe, and the speed data of the fan are comprehensively utilized to achieve accurate fault location. First, a fault diagnosis model based on support vector machine is established, and the time domain features (root mean square value, peak factor, waveform factor, and pulse factor) and frequency domain features (center of gravity frequency, mean square frequency, and frequency band energy distribution) in the vibration feature set are used as the main input features. At the same time, the pressure data and speed data are used as auxiliary features to construct a multidimensional feature space. In the fault location process, the system first performs anomaly detection on the vibration feature set of each preset component. By comparing with the pre-established healthy status baseline, it is determined whether there is abnormal vibration. When an abnormality is detected, the system further analyzes the specific manifestations of the vibration feature. For example, for a compressor, if it is found that the high-frequency band energy ratio is abnormally increased, and the peak factor is significantly increased, combined with the pressure data showing the inlet pressure fluctuation, it may indicate that there is a valve fault. For a fan, if the vibration feature shows that the low-frequency band energy ratio increases, and the speed data shows that the actual speed is lower than the set value, there may be motor performance degradation or bearing failure. The system also establishes a rule-based fault diagnosis knowledge base, which stores typical characteristic patterns of various faults. For example, when the vibration characteristics of the refrigeration pipe show increased high-frequency vibration and the pressure data shows increased pressure fluctuations, it may indicate abnormal refrigerant flow or system blockage. By matching the current state with the fault pattern in the knowledge base, the system can quickly locate the possible fault type and location. After completing the fault location, the system automatically generates a fault detection report. The report content includes but is not limited to: (1) Determination of the fault location, indicating the specific preset component location; (2) Determination of the fault type, explaining the specific manifestation of the fault; (3) Description of the fault characteristics, listing the key abnormal characteristic data; (4) Assessment of the severity of the fault, grading based on the degree to which the characteristics deviate from the normal value; (5) Maintenance suggestions, providing corresponding maintenance plans based on the type and severity of the fault.

[0074] Based on the above embodiment, as another optional embodiment, the step of locating the fault based on each vibration feature set, pressure data and rotation speed data and generating a fault detection report for the dehumidifier may further include the following steps:

[0075] Step 501: Determine the failure probability of each preset component based on each vibration feature set, pressure data, and rotation speed data.

[0076] Specifically, the embodiment of the present application uses a multi-state hidden Markov model to model and calculate the failure probability of the preset components of the dehumidifier. Since the failure evolution of the equipment has the characteristics of time sequence and concealment, the use of the hidden Markov model can effectively describe the dynamic change process of the equipment state and infer the internal state through observable data.

[0077] A multi-state hidden Markov model is constructed based on the vibration feature set of each preset component. For each preset component, its possible working state is defined as a hidden state, including multiple discrete states such as normal state, slight fault state, moderate fault state and severe fault state. The system uses the vibration feature set in historical data for model training, estimates the initial state probability distribution and the transition probability between states through the Baum-Welch algorithm, and establishes the initial state transition model. For example, for a compressor, its state may include normal operation, slight valve leakage, severe valve leakage, etc.; for a fan, its state may include normal operation, early bearing wear, severe bearing damage, etc.

[0078] Next, the real-time collected pressure data and speed data are input into the hidden Markov model as an observation sequence. The state probability distribution at each moment is calculated through the forward-backward algorithm, and the state transfer matrix is ​​updated. At the same time, the system calculates the observation probability matrix based on the observation data sequence and the corresponding state sequence. The matrix describes the probability of observing a certain data under a specific state. For example, when the compressor is in a valve leakage state, the probability of pressure data fluctuations will increase; when there is a fault in the fan bearing, the speed data may fluctuate or decrease.

[0079] The Viterbi algorithm is then used to calculate the most likely state sequence based on the updated state transition matrix and observation probability matrix. The Viterbi algorithm uses a dynamic programming method to find the optimal path among all possible state sequences, that is, the state sequence with the highest probability of the observation sequence. The system combines the obtained state sequence with the predefined state-fault mapping relationship to calculate the failure probability of each preset component. For example, if the state sequence shows that a component is frequently in an abnormal state, the probability of its corresponding fault type will increase accordingly.

[0080] Step 502: Classify the fault levels of the preset components according to the fault probability, and establish a priority queue of the faulty components.

[0081] Specifically, the fault level classification standard is set according to the fault probability: when the fault probability is less than 0.3, it is judged as a normal state; when the fault probability is between 0.3-0.6, it is judged as a mild fault; when the fault probability is between 0.6-0.8, it is judged as a moderate fault; and when the fault probability is greater than 0.8, it is judged as a severe fault. The setting of this classification standard takes into account the safety margin of equipment operation and the economy of maintenance. Based on the fault level classification results, the system uses the priority queue data structure to establish a priority queue for faulty components. The priority queue is implemented using a max-heap, and the fault probability is used as the priority weight. The higher the fault probability, the higher the priority. The system first inserts all preset components whose fault levels are not in the normal state into the priority queue. Each element in the queue contains information such as component identification, fault probability, and fault level. Through heap sorting, the system can quickly obtain the faulty component with the highest current priority.

[0082] Step 503: Identify major faulty components and minor faulty components based on the priority queue.

[0083] Specifically, after the priority queue is established, the system identifies major faulty components and minor faulty components according to preset threshold conditions. Specifically, components with serious faults and moderate faults are identified as major faulty components, which need to be processed first; components with minor faults are identified as minor faulty components, which need to be continuously monitored. For example, when the failure probability of the compressor reaches 0.85, it will be identified as a major faulty component, and when the failure probability of the fan is 0.45, it will be identified as a minor faulty component.

[0084] Step 504: Generate a fault detection report including major faulty components, minor faulty components and corresponding maintenance suggestions.

[0085] Specifically, the system automatically generates a detailed fault detection report. The report first lists the specific information of the main faulty components, including component name, fault probability, fault level and corresponding fault characteristic description. For example, for a compressor with a fault probability of 0.85, the report will describe in detail its abnormal vibration characteristics, pressure fluctuations and other specific manifestations. Then the information of the secondary faulty components is listed, including the parameters and change trends that need to be focused on. For each faulty component, the system gives corresponding maintenance suggestions based on its fault characteristics and severity. For example, for the main faulty components, it is recommended to immediately shut down for maintenance or replace related components; for the minor faulty components, it is recommended to check or adjust them during the next planned maintenance.

[0086] Based on the above embodiment, as another optional embodiment, a dehumidifier fault detection method may further include the following process:

[0087] Specifically, in order to optimize the energy efficiency of the dehumidifier, the operating power of the dehumidifier can also be monitored and adjusted in real time. First, the humidity data of the air is collected by installing temperature and humidity sensors at the air inlet and outlet. By calculating the humidity difference between the air inlet and outlet and combining it with the air volume data, the real-time dehumidification amount is obtained. These two parameters together constitute the dehumidification load index of the dehumidifier, reflecting the actual demand for dehumidification in the current environment.

[0088] Based on the dehumidification load obtained, the system uses a thermodynamic model to calculate the theoretical minimum power threshold. Specifically, the required latent heat load is first calculated based on the humidity difference between the inlet and outlet, and then the theoretical performance coefficient of the refrigeration system is considered to obtain the minimum power threshold required to complete the current dehumidification task. For example, when the relative humidity at the inlet is 75%, the relative humidity at the outlet is 45%, and the dehumidification capacity is 2kg / h, the system calculates that the minimum power threshold required to complete the dehumidification task is 800W. This threshold represents the minimum power input required to complete the current dehumidification task under ideal conditions.

[0089] The actual operating power of the dehumidifier is monitored in real time. When the difference between the actual power and the calculated minimum power threshold exceeds the preset range, the power adjustment mechanism is triggered. For example, if the preset range is ±15%, when the actual power is 1000W and the minimum power threshold is 800W, the difference is 200W, which exceeds the preset range. At this time, the system calculates the power adjustment coefficient based on this difference. The calculation of the power adjustment coefficient takes into account the size and change trend of the difference, and uses the proportional-integral algorithm to ensure the smoothness and accuracy of the adjustment. According to the calculated power adjustment coefficient, the system dynamically adjusts the operating power of the dehumidifier, and can achieve power adjustment by adjusting the operating frequency of the compressor and the speed of the fan. For example, when the power adjustment coefficient indicates that the power needs to be reduced, the system will gradually reduce the operating frequency of the compressor and adjust the fan speed appropriately to ensure that the dehumidification effect is not significantly affected. The adjustment process adopts a progressive control strategy to avoid sudden changes causing shocks to the equipment.

[0090] See also Figure 2 , is a module schematic diagram of a dehumidifier fault detection system provided in an embodiment of the present application, wherein the system includes:

[0091] A first data acquisition module is used to acquire the current dehumidification mode and multi-dimensional indicator data of the dehumidifier, the multi-dimensional indicator data including first temperature and humidity data of the dehumidifier air inlet, second temperature and humidity data of the air outlet, refrigeration pipe surface temperature data and power data;

[0092] An anomaly detection module, used to perform anomaly detection based on dehumidification mode and multi-dimensional indicator data to obtain anomaly detection results;

[0093] The second data acquisition module is also used to acquire vibration data of each preset component in the dehumidifier, pressure data of the refrigeration pipe and speed data of the fan when the abnormal detection result is that the dehumidifier is operating abnormally;

[0094] A vibration data analysis module, used to perform time domain and frequency domain analysis on the vibration data of each preset component to obtain a vibration feature set of each preset component;

[0095] The fault report generation module is used to locate the fault based on each vibration feature set, pressure data and rotation speed data, and generate a fault detection report for the dehumidifier.

[0096] Optionally, the first data acquisition module is further used to acquire operating parameters and environmental parameters set by the user, the operating parameters including target humidity and wind speed level, and the environmental parameters including indoor temperature and relative humidity;

[0097] Determine the current dehumidification mode of the dehumidifier according to the operating parameters and the environmental parameters;

[0098] Determine the corresponding data sampling frequency and sampling duration according to the dehumidification mode;

[0099] Collect multi-dimensional indicator data according to data sampling frequency and sampling duration.

[0100] Optionally, the anomaly detection module is further used to calculate a ratio sequence of the first temperature and humidity data and the corresponding second temperature and humidity data, and calculate the energy efficiency ratio of the dehumidifier based on the power data;

[0101] Determine the corresponding standard index range according to the dehumidification mode. The standard index range includes the temperature and humidity ratio range of the air inlet and the air outlet, the surface temperature range of the refrigeration pipe, and the energy efficiency ratio range;

[0102] When any ratio in the ratio sequence exceeds the temperature and humidity ratio range, and / or the refrigeration pipe surface temperature data exceeds the refrigeration pipe surface temperature range, and / or the energy efficiency ratio exceeds the energy efficiency ratio range, the abnormal detection result is determined to be abnormal dehumidifier operation.

[0103] Optionally, the vibration data analysis module is further used to perform wavelet denoising on the vibration data of each preset component to obtain the vibration data after denoising;

[0104] Calculate the root mean square value, peak factor, waveform factor and pulse factor of the vibration data after noise reduction to obtain the time domain characteristics;

[0105] Perform fast Fourier transform on the noise-reduced vibration data to extract spectrum features;

[0106] Calculate the centroid frequency, mean square frequency and band energy distribution of the spectrum characteristics to obtain frequency domain characteristics;

[0107] The time domain features and frequency domain features corresponding to each preset component are combined to obtain a vibration feature set of each preset component.

[0108] Optionally, the fault report generating module is further used to determine the fault probability of each preset component based on each vibration feature set, pressure data and rotation speed data;

[0109] Classify the fault levels of each preset component according to the fault probability and establish a priority queue for the faulty components;

[0110] Identify major faulty components and minor faulty components based on priority queues;

[0111] Generate a fault detection report containing major faulty components, minor faulty components and corresponding repair suggestions.

[0112] Optionally, the fault report generation module is further used to construct a multi-state hidden Markov model based on each vibration feature set;

[0113] The pressure data and the speed data are input into the hidden Markov model as the observation sequence to obtain the state transfer matrix and the observation probability matrix;

[0114] The optimal state sequence is calculated based on the state transfer matrix and the observation probability matrix using the Viterbi algorithm, and the failure probability of each preset component is calculated in combination with the preset state-fault mapping relationship.

[0115] Optionally, the fault report generating module is further used to obtain the dehumidification load of the dehumidifier, where the dehumidification load includes the humidity difference between the air inlet and the air outlet and the dehumidification amount;

[0116] Calculate the minimum power threshold based on the dehumidification load;

[0117] When the difference between the current actual power of the dehumidifier and the minimum power threshold exceeds a preset range, a power adjustment coefficient is calculated based on the difference, and the power of the dehumidifier is adjusted according to the power adjustment coefficient.

[0118] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0119] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a dehumidifier fault detection method of the above embodiment. The specific execution process can be found in the specific description of the above embodiment, which will not be repeated here.

[0120] Please refer to Figure 3 The application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0121] The communication bus 302 is used to realize the connection and communication between these components.

[0122] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0123] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0124] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0125] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a dehumidifier fault detection method.

[0126] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program storing a dehumidifier fault detection method in the memory 305, and when executed by one or more processors 301, the electronic device 300 executes one or more methods in the above-mentioned embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0127] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0129] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0130] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0131] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0132] The above are only exemplary embodiments of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0133] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A dehumidifier fault detection method, characterized in that: The method comprises: Obtaining the current dehumidification mode and multi-dimensional indicator data of the dehumidifier, wherein the multi-dimensional indicator data includes first temperature and humidity data of the air inlet of the dehumidifier, second temperature and humidity data of the air outlet, refrigeration pipe surface temperature data, and power data; Calculating a ratio sequence of the first temperature and humidity data and the corresponding second temperature and humidity data, and calculating an energy efficiency ratio of the dehumidifier based on the power data; Determine a corresponding standard index range according to the dehumidification mode, wherein the standard index range includes a temperature and humidity ratio range between the air inlet and the air outlet, a refrigeration pipe surface temperature range, and an energy efficiency ratio range; When any ratio in the ratio sequence exceeds the temperature-humidity ratio range, and / or the refrigeration pipe surface temperature data exceeds the refrigeration pipe surface temperature range, and / or the energy efficiency ratio exceeds the energy efficiency ratio range, determining that the abnormal detection result is that the dehumidifier is operating abnormally; When the abnormality detection result is that the dehumidifier is operating abnormally, obtaining vibration data of each preset component in the dehumidifier, pressure data of the refrigeration pipe, and speed data of the fan; Performing time domain and frequency domain analysis on the vibration data of each of the preset components to obtain a vibration feature set of each of the preset components; Fault location is performed based on each of the vibration feature sets, the pressure data, and the rotational speed data, and a fault detection report of the dehumidifier is generated.

2. The fault detection method for a dehumidifier according to claim 1, characterized in that: The obtaining of the current dehumidification mode and multi-dimensional indicator data of the dehumidifier includes: Obtaining operating parameters and environmental parameters set by a user, wherein the operating parameters include target humidity and wind speed level, and the environmental parameters include indoor temperature and relative humidity; determining a current dehumidification mode of the dehumidifier according to the operating parameters and the environmental parameters; Determine the corresponding data sampling frequency and sampling duration according to the dehumidification mode; The multi-dimensional indicator data is collected according to the data sampling frequency and the sampling duration.

3. The fault detection method for a dehumidifier according to claim 1, characterized in that: The vibration data of each of the preset components are analyzed in the time domain and the frequency domain to obtain a vibration feature set of each of the preset components, including: Performing wavelet denoising processing on the vibration data of each of the preset components to obtain denoised vibration data; Calculate the root mean square value, peak factor, waveform factor and pulse factor of the vibration data after noise reduction to obtain the time domain characteristics; Performing fast Fourier transform on the noise-reduced vibration data to extract spectrum features; Calculating the center frequency, mean square frequency and frequency band energy distribution of the frequency spectrum feature to obtain frequency domain features; The time domain features and the frequency domain features corresponding to each preset component are combined to obtain a vibration feature set of each preset component.

4. The fault detection method for a dehumidifier according to claim 1, characterized in that: The fault location is performed based on each of the vibration feature sets, the pressure data, and the rotation speed data, and a fault detection report of the dehumidifier is generated, including: Determining the failure probability of each of the preset components based on each of the vibration feature sets, the pressure data, and the speed data; Classify the fault levels of each preset component according to the fault probability and establish a priority queue of the faulty component; identifying a major faulty component and a minor faulty component based on the priority queue; Generate a fault detection report containing major faulty components, minor faulty components and corresponding repair suggestions.

5. The fault detection method for a dehumidifier according to claim 4, characterized in that: The determining of the failure probability of each of the preset components based on each of the vibration feature sets, the pressure data, and the rotational speed data includes: Constructing a multi-state hidden Markov model based on each of the vibration feature sets; Input the pressure data and the speed data into the hidden Markov model as an observation sequence to obtain a state transfer matrix and an observation probability matrix; The optimal state sequence is calculated based on the state transfer matrix and the observation probability matrix using the Viterbi algorithm, and the failure probability of each preset component is calculated in combination with a preset state-fault mapping relationship.

6. The fault detection method for a dehumidifier according to claim 1, characterized in that: The method further comprises: Obtaining a dehumidification load of the dehumidifier, wherein the dehumidification load includes a humidity difference between an air inlet and an air outlet and a dehumidification amount; Calculating a minimum power threshold according to the dehumidification load; When the difference between the current actual power of the dehumidifier and the minimum power threshold exceeds a preset range, a power adjustment coefficient is calculated based on the difference, and the power of the dehumidifier is adjusted according to the power adjustment coefficient.

7. A fault detection system for a dehumidifier, characterized in that: The system comprises: A first data acquisition module is used to acquire the current dehumidification mode and multi-dimensional index data of the dehumidifier, wherein the multi-dimensional index data includes first temperature and humidity data of the air inlet of the dehumidifier, second temperature and humidity data of the air outlet, refrigeration pipe surface temperature data, and power data; An abnormality detection module is used to calculate the ratio sequence of the first temperature and humidity data and the corresponding second temperature and humidity data, and calculate the energy efficiency ratio of the dehumidifier based on the power data; determine the corresponding standard index range according to the dehumidification mode, and the standard index range includes the temperature and humidity ratio range of the air inlet and the air outlet, the refrigeration pipe surface temperature range and the energy efficiency ratio range; when any ratio in the ratio sequence exceeds the temperature and humidity ratio range, and / or the refrigeration pipe surface temperature data exceeds the refrigeration pipe surface temperature range, and / or the energy efficiency ratio exceeds the energy efficiency ratio range, determine that the abnormality detection result is that the dehumidifier is operating abnormally; A second data acquisition module is used to acquire vibration data of each preset component in the dehumidifier, pressure data of the refrigeration pipe, and speed data of the fan when the abnormality detection result is that the dehumidifier is operating abnormally; A vibration data analysis module, used to perform time domain and frequency domain analysis on the vibration data of each of the preset components to obtain a vibration feature set of each of the preset components; A fault report generating module is used to locate the fault based on each of the vibration feature sets, the pressure data and the rotation speed data, and to generate a fault detection report for the dehumidifier.

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

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-6.

Images