An air conditioner operation state monitoring method and system

Abstract

The present invention relates to the technical field of air conditioner operation state monitoring, and particularly to a method and system for monitoring the operation state of an air conditioner. The method includes the steps of: evenly dividing the pressure time series sequence of the air conditioner compressor into multiple pressure data segments, and denoting the pressure data segment including endpoints as the endpoint data segment; obtaining the degree of dispersion of the data points through the difference between the data points in the endpoint data segment and the overall endpoint data segment; obtaining the corresponding temperature data segment of the endpoint data segment in the temperature time series sequence; calculating the extension requirement degree of the data points in the endpoint data segment; determining the required length of each data point in the endpoint data segment for the extended data segment, where the required length is positively correlated with the extension requirement degree; and performing anomaly monitoring using the Z-Score algorithm after extending the endpoint data segment according to the required length of the extended data segment, so as to obtain the monitoring result of the air conditioner operation state, effectively improving the accuracy of the air conditioner operation state monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioner operation status monitoring, and in particular to an air conditioner operation status monitoring method and system. Background Art

[0002] The compressor is the core component of the air conditioner system. The compressor continuously compresses the refrigerant from a low-pressure state to a high-pressure state, thereby increasing its temperature and pressure, and releasing it into the condenser to complete the refrigeration cycle. If the compressor fails during the operation of the air conditioner, it will not only affect the normal operation of the compressor itself, but may also cause abnormal increase or decrease in the pressure within the air conditioner system, thereby triggering failures of other system components, and ultimately leading to failures of the air conditioner, posing serious safety hazards.

[0003] In the prior art, a variety of methods for monitoring the operation status of air conditioner compressors are provided. For example, the patent application document with the publication number CN115077031A discloses a compressor bus voltage control method, device and air conditioner. This application calculates the target bus voltage of the compressor by detecting the real-time bus voltage, phase current and motor speed of the air conditioner compressor; when it is monitored and calculated that the target bus voltage during the operation of the compressor is too high or too low, the abnormal situation of the target bus voltage is judged and confirmed according to the real-time bus voltage, so as to realize the monitoring of the air conditioner compressor.

[0004] However, the real-time bus voltage, phase current and motor speed used in the above prior art can only reflect the state of the compressor drive system, rather than the direct working state of the compressor itself or the entire air conditioner system, resulting in the monitoring results obtained not being able to comprehensively reflect the operation status of the air conditioner.

[0005] Based on this, how to accurately obtain the monitoring results of the air conditioner operation status is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0006] In order to solve the technical problem of how to accurately obtain the monitoring results of the air conditioner operation status, the present invention provides an air conditioner operation status monitoring method and system.

[0007] In a first aspect, the present invention provides an air conditioner operation status monitoring method, adopting the following technical solution:

[0008] An air conditioner operation status monitoring method includes the steps:

[0009] The pressure time series of the air conditioner compressor is evenly divided into multiple pressure data segments, and the pressure data segment containing endpoints is denoted as the endpoint data segment; the degree of dispersion of the data points is obtained through the difference between the data points in the endpoint data segment and the overall endpoint data segment; the temperature data segment corresponding to the endpoint data segment is obtained in the temperature time series; the degree of dispersion of the data points is corrected based on the number of abnormal data points in other pressure data segments and the correlation between the pressure data and the temperature data to obtain the extension requirement degree of the data points:

[0010] ; is the extension requirement degree of the th data point in the endpoint data segment, is the total number of data points other than the th data point in the endpoint data segment, is the degree of dispersion of the th data point in the endpoint data segment, is the number of pressure data segments, 、 are the numbers of abnormal data points in the endpoint data segment and the th pressure data segment respectively, 、 are the information entropy values of the endpoint data segment and the temperature data segment corresponding to the endpoint data segment respectively, is the exponential function with base e, is the linear normalization function; determine the required length of the extension data segment for each data point in the endpoint data segment, and the required length is positively correlated with the extension requirement degree; after extending the endpoint data segment according to the required length of the extension data segment, use the Z-Score algorithm for anomaly monitoring to obtain the monitoring result of the air conditioner operation status.

[0011] By combining the pressure data segment and the temperature data segment of the compressor, the present invention jointly determines the required length of the extension data segment for the target data point in the endpoint data segment, effectively improving the accuracy of the required length of the extension data segment for the target data point; then, based on the relatively accurate required length of the extension data segment, the endpoint data segment is extended, effectively reducing the error caused by the insufficient data points at the endpoint data segment in the pressure data segment, and determining the operation status of the air conditioner compressor based on the extended pressure data segment, which can effectively improve the accuracy of analyzing the air conditioner operation status.

[0012] According to an air conditioner operation status monitoring method provided by the present invention, the degree of dispersion of each data point in the endpoint data segment satisfies the relational expression:

[0013] ;

[0014] is the degree of dispersion of the th data point in the endpoint data segment, is the total number of data points in the endpoint data segment except for the data point, is the pressure value of the data point, is the pressure value of the th data point in the endpoint data segment except for the data point, is the variance of the pressure values of all data points in the endpoint data segment, is the variance of the pressure values in the endpoint data segment except for the data point, is the sampling time interval between the data point and the endpoint in the endpoint data segment, is a hyperparameter, is a linear normalization function.

[0015] The present invention provides a method for calculating the dispersion degree of precise data points. By analyzing the differences between the data points in the endpoint data segment and the overall endpoint data segment, the dispersion degree of each data point in the endpoint data segment can be accurately obtained.

[0016] According to an air conditioner operation state monitoring method provided by the present invention, the number of abnormal data points in the pressure data segment is obtained by the box plot method.

[0017] According to an air conditioner operation state monitoring method provided by the present invention, the determination of the required length of each data point in the endpoint data segment for the extended data segment includes: ; is the required length of the th data point in the endpoint data segment for the extended data segment, is the extension requirement degree of the th data point in the endpoint data segment, is the preset extended data segment length, is the floor function symbol.

[0018] According to an air conditioner operation state monitoring method provided by the present invention, extending the endpoint data segment according to the required length of the extended data segment includes: taking the maximum value of the required lengths corresponding to each data point in the endpoint data segment as the extension length of the endpoint data segment, and continuously collecting data points to extend the endpoint data segment.

[0019] By calculating the required length of each data point in the endpoint data segment for the extended data segment, the present invention obtains the extension length of the endpoint data segment, which can make the calculation of the required length of the extended data segment more flexible, obtain more complete pressure data, and prepare for subsequent determination of the operation state of the air conditioner.

[0020] According to an air conditioner operation status monitoring method provided by the present invention, after extending the endpoint data segment according to the required length of the extended data segment, the Z-Score algorithm is used for anomaly monitoring to obtain the air conditioner operation status monitoring result, including: calculating the scores of each data point in the extended pressure time series using the Z-Score algorithm; if the score of a data point is greater than the preset score threshold, the air conditioner operation status monitoring result is abnormal; otherwise, the air conditioner operation status monitoring result is normal.

[0021] The present invention determines the operation status of a data point through the comparison result between the preset score threshold and the score of the data point, and can adjust the score threshold according to actual needs to achieve the best classification or detection effect and reduce the situations of false alarms and missed detections.

[0022] According to an air conditioner operation status monitoring method provided by the present invention, after obtaining the air conditioner operation status monitoring result, it further includes: in response to the air conditioner operation status monitoring result being abnormal, issuing an air conditioner anomaly warning.

[0023] The present invention obtains and analyzes data in real time during the operation of the compressor, thereby timely discovering potential problems such as air conditioner anomalies and giving warnings. Through preventive maintenance strategies, the occurrence of compressor failures can be reduced, and the reliability and service life of the air conditioner can be improved.

[0024] In a second aspect, the present invention provides an air conditioner operation status monitoring system, adopting the following technical solution:

[0025] An air conditioner operation status monitoring system includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned air conditioner operation status monitoring method is implemented.

[0026] By adopting the above technical solution, the above-mentioned air conditioner operation status monitoring method is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0027] The present invention has the following technical effects:

[0028] Based on the above technical solutions, a method and a system for monitoring the operating state of an air conditioner provided by the present invention have the following beneficial effects: when analyzing the operating state of the compressor, an accurate calculation method for the required length of the extended data segment is provided, comprehensively considering the data characteristics in the pressure data segment and the temperature data, effectively improving the accuracy of calculating the required length of the extended data segment; then, based on the required length of the extended data segment with relatively high accuracy, the endpoint data segment is extended, effectively reducing the monitoring error caused by the insufficient number of data points at the endpoint data segment in the pressure data segment, and determining the operating state of the compressor based on the extended pressure data, which can effectively improve the accuracy of the obtained monitoring result of the operating state of the air conditioner. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understandable. In the drawings, several embodiments of the present invention are shown by way of example and not limitation, and the same or corresponding reference numerals indicate the same or corresponding parts.

[0030] Figure 1 It is a flowchart of a method for monitoring the operating state of an air conditioner provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0032] It should be understood that when the claims, specifications, and drawings of the present invention use terms such as "first" and "second", they are only used to distinguish different objects and not to describe a specific order. The terms "including" and "comprising" used in the specifications and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0033] The compressor is the core component of the air conditioner system. The compressor continuously compresses the refrigerant from a low-pressure state to a high-pressure state, thereby increasing its temperature and pressure and releasing it into the condenser to complete the refrigeration cycle. If a fault occurs during the operation of the compressor, it will not only affect the normal operation of the compressor itself, but also may cause abnormal increase or decrease in the pressure within the air conditioner system, thereby triggering faults in other system components, and ultimately resulting in faults in the air conditioner, posing serious safety hazards.

[0034] The pressure data generated during the operation of an air conditioner compressor can directly reflect the working state inside the air conditioner compressor system. By monitoring the pressure data, the fault points in the compressor system, such as blockage, leakage, abnormal pressure, etc., can be visually identified.

[0035] The standard score (Z-Score) algorithm can effectively identify outliers in a dataset. By calculating the deviation degree of each data point from the average value of the dataset, it can quickly locate the data points that deviate from the normal level.

[0036] Based on this, an embodiment of the present invention discloses a method for monitoring the operating state of an air conditioner. By processing the time series of pressure data of the compressor through the Z-Score algorithm, abnormal data in the compressor can be identified, thereby accurately obtaining the operating monitoring result of the air conditioner. For details, please refer to Figure 1 , Figure 1 which is a flowchart of a method for monitoring the operating state of an air conditioner provided by an embodiment of the present invention. The method specifically includes the following steps.

[0037] S1: Divide the time series of pressure of the air conditioner compressor into multiple pressure data segments, and record the pressure data segment containing endpoints as the endpoint data segment.

[0038] Among them, the pressure can be the suction pressure, the discharge pressure, etc.; specifically, it can be set according to actual needs, and the embodiments of the present invention do not make excessive restrictions here.

[0039] Among them, the pressure data segment includes the endpoint data segment and other pressure data segments, and the number of data points in each data segment is the same; the number of data points in the pressure data segment can be set to 60, specifically, it can be set according to actual needs, and the embodiments of the present invention do not make excessive restrictions here.

[0040] Exemplarily, the pressure sensor data can be collected through a pressure sensor, and the time series of pressure of the compressor can be obtained based on the analog-to-digital conversion device for analog-to-digital conversion of the pressure sensor data.

[0041] Among them, when collecting the pressure sensor data of the compressor through the pressure sensor, the collection duration can be 30 minutes, and the collection frequency can be once per second. The collection duration and the collection frequency can be specifically set according to actual needs, and the embodiments of the present invention do not make excessive restrictions here.

[0042] Specifically, when dividing the time series of pressure, the time series of pressure can be divided into multiple pressure data segments based on the preset length of the pressure data segment.

[0043] It can be understood that the time series of pressure has two endpoints, namely the start and the end. Therefore, there are also two endpoint data segments containing endpoints.

[0044] Exemplarily, in the embodiments of the present invention, the endpoint data segment may be a start data segment and / or an end data segment. Among them, the start data segment is the start data point and several data points around the start data point in the pressure data segment, and the end data segment is the end data point and several data points around the end data point in the pressure data segment.

[0045] For the sake of easy understanding, in the embodiments of the present invention, the start data segment or the end data segment is collectively referred to as the endpoint data segment for description, but it does not mean that the embodiments of the present invention are only limited to this.

[0046] Based on the above method, the pressure data segment can be obtained. However, in the pressure time series generated by the operation of the compressor, the endpoint data segment often contains important information, which may reflect the turning point of the compressor state change. However, when analyzing the endpoint data based on the data points near the endpoint in the pressure time series, usually only one-sided data can be used for the analysis of the endpoint, resulting in a low accuracy of the monitoring result of the operating state of the endpoint. Therefore, it is necessary to extend the endpoint, that is, to perform the following steps.

[0047] S2: Obtain the dispersion degree of the data point through the difference between the data point in the endpoint data segment and the whole of the endpoint data segment.

[0048] It should be noted that the required length of the extended data segment of the data point is related to the dispersion degree of the data point. The higher the dispersion degree of the data point in the endpoint data segment, it means that the numerical difference between the data point and other data points in the endpoint data segment is larger, and the dispersion degree is also higher. In order to reduce the boundary effect, the required length of the extended data segment is also higher.

[0049] Based on this, in order to accurately obtain the required length of the extended data segment of the data point in the endpoint data segment, the embodiments of the present invention can determine the dispersion degree of the data point in the endpoint data segment by analyzing the degree of data change.

[0050] It can be understood that in the endpoint data segment of the pressure data segment, the dispersion degree between the current data point and other data points can reflect the deviation between the pressure value of the current data point and the pressure values of other data points.

[0051] Exemplarily, in the embodiments of the present invention, to determine the dispersion degree of each data point in the endpoint data segment, the following formula can be specifically referred to:

[0052] ;

[0053] is the dispersion degree of the data point in the endpoint data segment, is the total number of data points in the endpoint data segment except the data point, is the The pressure value of the data point, is the pressure value of the th data point in the endpoint data segment excluding the th data point, is the variance of the pressure values of all data points in the endpoint data segment, is the variance of the pressure values in the endpoint data segment excluding the th data point, is the sampling time interval between the th data point and the endpoint in the endpoint data segment, is a hyperparameter, is a linear normalization function.

[0054] Among them, the sampling time interval between the th data point and the endpoint in the endpoint data segment can be obtained by taking the absolute value of the difference in the sampling time between the th data point and the endpoint in the endpoint data segment.

[0055] In the above formula, the hyperparameter can prevent the denominator in the formula from becoming zero when the current data point is an endpoint. The value of the hyperparameter can be set to 0.01, and the specific value of the hyperparameter can be set according to actual needs, and the embodiments of the present invention do not limit it too much here.

[0056] The smaller the sampling time interval between the th data point and the endpoint, the closer the distance between the th data point and the endpoint is, the stronger the boundary effect at the

[0057] th data point is, and the higher the demand for continuation is. represents the sum of the differences between the pressure value of the th data point and the pressure values of all data points in the endpoint data segment excluding the th data point. The larger this value is, the greater the numerical difference between the pressure value of the th data point and other data points in the endpoint data segment is, that is, the greater the difference between the

[0058] th data point and the entire endpoint data segment is, and the corresponding degree of isolation and dispersion is greater. represents the difference between the variance of the pressure values of all data points in the endpoint data segment and the variance of the pressure values of all data points in the endpoint data segment excluding the th data point. The larger this value is, the greater the degree of data dispersion in the entire endpoint data segment will be caused by the The greater the numerical difference between a data point and other data points in the endpoint data segment, the greater its corresponding degree of isolation and dispersion.

[0059] Indicates the trend of the data point in the endpoint data segment. The larger this value, the more dispersed the trend of the data point in the endpoint data segment is.

[0060] Based on the above method, the dispersion degree of each data point in the endpoint data segment can be obtained. However, when calculating the dispersion degree of the data points in the endpoint data segment, it is based on the pressure data change characteristics of the endpoint data segment. If there are many abnormal data in the endpoint data segment, it may lead to an inaccurate determination of the dispersion degree of the data points, thereby affecting the accuracy of anomaly monitoring. Therefore, it is also necessary to obtain the mutual relationship between the pressure data and other parameters to verify the dispersion degree of the pressure data, that is, to perform the following steps.

[0061] S3: Obtain the temperature data segment corresponding to the endpoint data segment in the temperature time series, and calculate the extension requirement degree of each data point in the endpoint data segment.

[0062] Among them, the length of the temperature data segment is the same as that of the endpoint data segment, and the data values in the temperature data segment and the endpoint data segment correspond one by one.

[0063] It should be noted that the suction pressure in the compressor corresponds to the evaporation temperature, and the discharge pressure corresponds to the condensation temperature. As the suction pressure decreases, the saturation vapor pressure of the refrigerant also decreases accordingly, resulting in a decrease in the evaporation temperature. As the condensation temperature increases, the pressure of the refrigerant in the condenser also increases accordingly, and the corresponding discharge pressure will increase accordingly. Therefore, there is a good positive correlation between the pressure data and the corresponding temperature data in the air-conditioning compressor.

[0064] Based on this, in order to improve the accuracy of calculating the required length of the extended data segment of the data point, the embodiment of the present invention can also perform a comparative analysis by obtaining other pressure data segments in the pressure time series except the endpoint data segment and the endpoint data segment, and correct the dispersion degree with the compressor temperature data correlated with the pressure of the compressor. Combine other pressure data segments and temperature data segments to jointly determine the required length of the extended data segment, so that the extended data segment is more in line with the actual situation and improves the accuracy of anomaly analysis.

[0065] Exemplarily, the temperature data of the compressor can be collected by a temperature sensor, and then the temperature sensor data is converted by an analog-to-digital conversion device to obtain the temperature time series of the compressor. The data values in the obtained temperature time series and the pressure time series correspond one by one.

[0066] Among them, when collecting the temperature data of the compressor through the temperature sensor, the collection duration and collection frequency can refer to the collection duration and collection frequency of the above-mentioned pressure data, which will not be elaborated in this embodiment of the present invention.

[0067] For example, in the same time period, if the endpoint data segment in the obtained pressure data segment of the compressor contains 60 data points, then the temperature data segment can be obtained within the time period where the pressure data segment is located, and the obtained temperature data segment also contains 60 data points.

[0068] Exemplarily, when determining the extension requirement degree of the data points, other pressure data segments except the endpoint data segment can be obtained in the pressure data segment, and the number of abnormal data points in the other pressure data segments can be determined; based on the number of abnormal data points in the other pressure data segments and the correlation between the pressure data and the temperature data, the dispersion degree of the data points is corrected to obtain the extension requirement degree of the data points.

[0069] Exemplarily, in this embodiment of the present invention, the number of abnormal data points in the pressure data segment can be obtained by the box plot method; the specific steps of obtaining the number of abnormal data points by the box plot method can be realized by the prior art, which will not be elaborated in this embodiment of the present invention.

[0070] It can be understood that the number of pressure data segments is determined by the length of the pressure time series, and the number of other pressure data segments except the endpoint data segment is the total number of pressure data segments minus 1.

[0071] Exemplarily, in this embodiment of the present invention, to determine the extension requirement degree of the data points, the following relational expression can be specifically referred to:

[0072] ;

[0073] is the extension requirement degree of the th data point in the endpoint data segment, is the total number of data points in the endpoint data segment except the th data point, is the dispersion degree of the th data point in the endpoint data segment, is the number of pressure data segments, is the th number of abnormal data points in the pressure data segment, is the number of abnormal data points in the endpoint data segment, is the information entropy value of the endpoint data segment, is the information entropy value of the temperature data segment corresponding to the endpoint data segment, is the exponential function with e as the base, is the linear normalization function, is the absolute value symbol.

[0074] In the above formula, represents the sum value of the dispersion degree of all data points in the endpoint data segment. The larger this value is, the more dispersed the data points in the endpoint data segment are, and the higher the demand degree of the th data point for the extended data segment.

[0075] represents the sum value of the difference between the number of abnormal data points in the endpoint data segment and the number of abnormal data points in each pressure data segment. The larger this value is, the more dispersed the data points in the endpoint data segment are and the greater the degree of abnormality.

[0076] represents the absolute value of the difference between the information entropy of the data points in the endpoint data segment and the information entropy of the data points in the temperature data segment. The larger this value is, the smaller the correlation between the data points in the endpoint data segment and the corresponding temperature data segment in the same time period, and the lower the demand degree of the current data point for the extended data segment.

[0077] After determining the extension demand degree of each data point in the endpoint data segment based on the above formula, the demand length of the extended data segment can be determined based on the extension demand degree and the endpoint data segment can be extended, that is, the following steps are executed.

[0078] S4: Determine the demand length of each data point in the endpoint data segment for the extended data segment. The demand length is positively correlated with the extension demand degree; extend the endpoint data segment according to the demand length of the extended data segment.

[0079] It should be noted that the greater the extension demand degree of the data points in the endpoint data segment, the longer the demand length of the corresponding extended data segment.

[0080] Exemplarily, in the embodiments of the present invention, to determine the demand length of the extended data segment of the data point, the following formula can be specifically referred to:

[0081] ;

[0082] is the demand length of the th data point in the endpoint data segment for the extended data segment, is the extension demand degree of the th data point in the endpoint data segment, is the preset length of the extended data segment, is the floor symbol.

[0083] Among them, the preset length of the extended data segment can be set to 100. The length of the extended data segment can be specifically set according to actual needs, and the embodiments of the present invention do not make too many restrictions here.

[0084] The value 0.5 in the above formula is the initial value of the length of the extended data segment calculated and is rounded to better obtain the required length of the extended data segment for the current data point.

[0085] When determining the required length of the extended data segment for a data point based on the above steps, since the endpoint data segment contains multiple data points, the required lengths of the extended data segments for each of the multiple data points in the endpoint data segment can be obtained based on the above steps. To better meet the required lengths of the extended data segments for all data points, the maximum value among the required lengths of the extended data segments for each of the multiple data points can be determined as the required length of the extended data segment for the endpoint data segment, and the endpoint data segment is extended based on the required length of the extended data segment. In this way, the finally obtained required length of the extended data segment can not only extend the endpoint data segment but also avoid data redundancy, preparing for subsequent determination of the operating state of the compressor based on this.

[0086] Based on this, the embodiment of the present invention can obtain the maximum value of the required length of the extended data segment for the data points in the endpoint data segment, extend the endpoint data segment based on the required length of the extended data segment for the data point, and then obtain a more accurate compressor state analysis result based on the extended endpoint data segment.

[0087] Exemplarily, in the embodiment of the present invention, extending the endpoint data segment according to the required length of the extended data segment includes: taking the maximum value of the required lengths corresponding to each data point in the endpoint data segment as the extended length of the endpoint data segment, and continuously collecting data points to extend the endpoint data segment.

[0088] It can be understood that the extended lengths of the starting data segment and / or the ending data segment can be obtained respectively based on the above steps. In the case where the endpoint data segment of the pressure data segment of the compressor is the starting data segment and the ending data segment, the starting data segment and the ending data segment can be extended respectively based on the required length of the extended data segment; in the case where the data segment of the pressure data segment of the compressor is the starting data segment or the ending data segment, the starting data segment or the ending data segment is extended based on the required length of the extended data segment. When extending the starting data segment, data points can be continuously collected on the left side of the starting point; when extending the ending data segment, data points can be continuously collected on the right side of the ending point.

[0089] After extending the endpoint data segment of the pressure time series of the air-conditioning compressor, the following steps are continued.

[0090] S5: Use the Z-Score algorithm to perform anomaly monitoring on the pressure time series after extending the endpoint data segment to obtain the air-conditioning operation state monitoring result.

[0091] It can be understood that the extended pressure time series obtained based on the above steps includes an extended starting data segment, an extended ending data segment, and an initial pressure time series.

[0092] Exemplarily, in the embodiments of the present invention, after extending the endpoint data segment according to the required length of the extended data segment, the Z-Score algorithm is used for anomaly monitoring to obtain the monitoring result of the air conditioner operation state, including: calculating the scores of each data point in the extended pressure time series using the Z-Score algorithm; if the score of a data point is greater than a preset score threshold, the monitoring result of the air conditioner operation state is abnormal; otherwise, the monitoring result of the air conditioner operation state is normal.

[0093] Among them, the preset score threshold can be set to 2.5, and can be specifically set according to actual needs. The embodiments of the present invention do not limit this too much here.

[0094] Specifically, when calculating the scores of each data point in the extended pressure time series using the Z-Score algorithm, the data point window length of the extended pressure time series can be preset, and the mean and standard deviation in the window can be determined; the difference between the data point and the window mean is recorded as the anomaly index of the data point, and the score of the data point is obtained through the ratio of the anomaly index of the data point to the window standard deviation.

[0095] Among them, the window length can be set to 31, and can be specifically set according to actual needs. When obtaining the window of a data point, other data points can be obtained equally on both sides of the data point with the current data point as the center to construct the window of the current data point.

[0096] It should be noted that when determining the operation state of the compressor for any data point based on the extended pressure time series, the abnormal state of the compressor operation state can be warned, and the operator can be notified in time for processing, so as to effectively avoid the occurrence of accidents and reduce the wear of the compressor.

[0097] Exemplarily, after obtaining the monitoring result of the air conditioner operation state, it further includes: in response to the monitoring result of the air conditioner operation state being abnormal, issuing an air conditioner abnormality warning.

[0098] Among them, the air conditioner abnormality warning can be set as a voice alarm or a signal lamp alarm, and can be specifically set according to actual needs. The embodiments of the present invention do not limit this too much here.

[0099] Exemplarily, in the embodiments of the present invention, after issuing the air conditioner abnormality warning, the number of air conditioner abnormality warnings can also be counted. If the number of abnormality warnings exceeds the air conditioner warning threshold, the compressor can be directly stopped, and the information of the data point corresponding to the compressor warning generation can be recorded and reported.

[0100] Exemplarily, the information of the data points may include the pressure value of the compressor, the temperature value, the time and frequency of warning generation, etc., which can be specifically set according to actual needs.

[0101] Among them, the air-conditioning warning threshold can be specifically set according to actual needs, and the embodiments of the present invention do not limit it too much here.

[0102] It can be seen that in the embodiments of the present invention, when analyzing the operating state of the air-conditioning compressor, the pressure time series of the air-conditioning compressor can be evenly divided into multiple pressure data segments, and the pressure data segment including endpoints is denoted as the endpoint data segment; the dispersion degree of the data points is obtained through the difference between the data points in the endpoint data segment and the whole of the endpoint data segment; the temperature data segment corresponding to the endpoint data segment is obtained in the temperature time series; the dispersion degree of the data points is corrected based on the number of abnormal data points in other pressure data segments and the correlation between the pressure data and the temperature data to obtain the extension requirement degree of the data points:

[0103] ; is the extension requirement degree of the th data point in the endpoint data segment, is the total number of data points other than the th data point in the endpoint data segment, is the th data point in the dispersion degree in the endpoint data segment, is the number of pressure data segments, 、 are the number of abnormal data points in the endpoint data segment and the th pressure data segment respectively, 、 are the information entropy values of the endpoint data segment and the temperature data segment corresponding to the endpoint data segment respectively, is the exponential function with base e, is the linear normalization function; determine the required length of each data point in the endpoint data segment for the extended data segment, and the required length is positively correlated with the extension requirement degree; after extending the endpoint data segment according to the required length of the extended data segment, use the Z-Score algorithm for anomaly monitoring to obtain the monitoring result of the air-conditioning operating state.

[0104] In this way, through an accurate calculation method for the required length of the extended data segment provided by the embodiments of the present invention, the data characteristics in the pressure data segment and the temperature data are comprehensively considered, effectively improving the accuracy of the required length of the extended data segment; then, based on the required length of the extended data segment with higher accuracy, the endpoint data segment is extended, effectively reducing the error caused by the insufficient data points at the endpoint data segment in the pressure data segment, and determining the operating state of the compressor based on the extended pressure data segment, effectively improving the accuracy of the monitoring result of the air-conditioning operating state.

[0105] An embodiment of the present invention also discloses an air conditioner operating state monitoring system, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, an air conditioner operating state monitoring method according to the present invention is implemented.

[0106] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, module, or both. Any such computer storage medium can be part of the device or accessible or connectable to the device.

[0107] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

[0108] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for monitoring the operating status of an air conditioner, characterized in that: include: The pressure time series of the air-conditioning compressor is divided into a plurality of pressure data segments, and the pressure data segment containing the endpoint is recorded as the endpoint data segment; The discrete degree of the data point is obtained by the difference between the data point in the endpoint data segment and the endpoint data segment as a whole; the temperature data segment corresponding to the endpoint data segment is obtained in the temperature time series; the discrete degree of the data point is corrected based on the number of abnormal data points in other pressure data segments and the correlation between pressure data and temperature data, and the extension requirement of the data point is obtained: ; The endpoint data segment The extension requirement of data points, For endpoint data segments except The total number of data points outside the data point, The endpoint data segment The degree of dispersion of the data points, is the number of pressure data segments, , They are endpoint data segment, The number of abnormal data points in a pressure data segment, , are the information entropy values ​​of the endpoint data segment and the temperature data segment corresponding to the endpoint data segment, is an exponential function with base e, is a linear normalized function; the required length of each data point in the endpoint data segment for the extended data segment is determined, and the required length is positively correlated with the extended demand degree; after extending the endpoint data segment according to the required length of the extended data segment, the Z-Score algorithm is used for abnormal monitoring to obtain the air conditioning operation status monitoring result.

2. The method for monitoring the operating status of an air conditioner according to claim 1, characterized in that: The discrete degree of each data point in the endpoint data segment satisfies the relationship: ； The endpoint data segment The degree of dispersion of the data points, For endpoint data segments except The total number of data points outside the data point, For the The pressure value of the data point, For each endpoint data segment except Data points outside the The pressure value of the data point, is the pressure value variance of all data points in the endpoint data segment, For each endpoint data segment except The variance of the pressure values ​​outside the data points, For the The sampling time interval between the data point and the endpoint in the endpoint data segment, is a hyperparameter, is a linear normalization function.

3. The method for monitoring the operating status of an air conditioner according to claim 1, characterized in that: The number of abnormal data points in the pressure data segment is obtained by the box plot method.

4. The method for monitoring the operating status of an air conditioner according to claim 1, characterized in that: The step of determining the required length of the extended data segment for each data point in the endpoint data segment includes: ； The endpoint data segment The required length of the extended data segment by the data point, The endpoint data segment The extension requirement of data points, To preset the length of the extended data segment, The floor symbol.

5. The method for monitoring the operating status of an air conditioner according to claim 1, characterized in that: Extend the endpoint data segment according to the required length of the extended data segment, including: The maximum value of the required length corresponding to each data point in the endpoint data segment is used as the extended length of the endpoint data segment, and the endpoint data segment is extended in accordance with the collected data points.

6. The method for monitoring the operating status of an air conditioner according to claim 5, characterized in that: The method of using the Z-Score algorithm to perform abnormal monitoring after extending the endpoint data segment according to the required length of the extended data segment to obtain the air conditioner operation status monitoring result includes: The Z-Score algorithm is used to calculate the score of each data point in the extended pressure time series; if the score of the data point is greater than the preset score threshold, the air conditioner operation status monitoring result is abnormal; otherwise, the air conditioner operation status monitoring result is normal.

7. The method for monitoring the operating status of an air conditioner according to claim 6, characterized in that: The air conditioner operation status monitoring result is obtained, and then the following steps are further included: In response to the air-conditioning operation status monitoring result being abnormal, an air-conditioning abnormality warning is issued.

8. An air conditioning operation status monitoring system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an air conditioning operation status monitoring method according to any one of claims 1-7 is implemented.

Images