CN115013936A - Fault detection method and device for air conditioning equipment and storage medium - Google Patents
Fault detection method and device for air conditioning equipment and storage medium Download PDFInfo
- Publication number
- CN115013936A CN115013936A CN202210757221.8A CN202210757221A CN115013936A CN 115013936 A CN115013936 A CN 115013936A CN 202210757221 A CN202210757221 A CN 202210757221A CN 115013936 A CN115013936 A CN 115013936A
- Authority
- CN
- China
- Prior art keywords
- normal
- equipment
- rule
- abnormal
- rules
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 106
- 238000004378 air conditioning Methods 0.000 title claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 112
- 238000000034 method Methods 0.000 claims abstract description 64
- 230000008569 process Effects 0.000 claims abstract description 22
- 238000005065 mining Methods 0.000 claims description 46
- 238000012790 confirmation Methods 0.000 claims description 30
- 238000007781 pre-processing Methods 0.000 claims description 25
- 238000004422 calculation algorithm Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 238000009795 derivation Methods 0.000 claims description 5
- 230000006698 induction Effects 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000002085 persistent effect Effects 0.000 description 4
- 230000000717 retained effect Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000013508 migration Methods 0.000 description 3
- 230000005012 migration Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005057 refrigeration Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000005293 physical law Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000002355 dual-layer Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/30—Control or safety arrangements for purposes related to the operation of the system, e.g. for safety or monitoring
- F24F11/32—Responding to malfunctions or emergencies
- F24F11/38—Failure diagnosis
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
- F24F11/00—Control or safety arrangements
- F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
- F24F11/63—Electronic processing
- F24F11/64—Electronic processing using pre-stored data
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the application discloses a fault detection method, a fault detection device and a storage medium of air conditioning equipment, which can detect system faults before serious faults occur to the air conditioning equipment and improve the reliability of the air conditioning equipment. The fault detection method comprises the following steps: taking normal equipment operation data as a reference, and comparing the normal equipment operation data with the equipment operation data to be detected to obtain a parameter offset trend of the equipment to be detected, wherein the parameter offset trend comprises an offset direction and an offset degree, and the normal equipment operation data are data of various physical parameters recorded in the operation process of the normal equipment; and carrying out fault detection on the parameter offset trend of the equipment to be detected by using rules in an association rule base to obtain a detection result, wherein the association rule base comprises normal rules and abnormal rules.
Description
Technical Field
The present application relates to the field of fault detection technologies for air conditioners, and in particular, to a fault detection method, a fault detection apparatus, and a storage medium for an air conditioner.
Background
An air conditioning system is a complex equipment system, and the operation state of the air conditioning system is influenced not only by internal factors of the system, such as user set parameters, but also by external environmental factors, such as environmental working condition parameters. In the operation process of the air conditioning system, the air conditioning system is in a sub-health state due to slight faults, in such a case, although the air conditioning system can still continue to operate, the system performance is reduced, and as the system load and the operation time length are increased, the system faults are gradually changed from slight faults to serious faults, so that the system cannot operate.
In the process of implementing the present application, the inventors found that at least the following technical problems exist in the prior art: in the related fault detection technology, it is usually difficult to detect a slight fault of a system in a "sub-health state", and only when the system has a serious fault, a user or an equipment operation maintenance worker can find the system fault, while the air conditioning equipment can continue to operate in the "sub-health" state, but the equipment reliability is reduced, and the originally slight fault may be upgraded and deteriorated at any time, which brings extra economic loss to the user.
Therefore, it is desirable to design a detection method capable of effectively detecting a failure before a serious failure occurs in an air conditioning apparatus, thereby improving the reliability of the apparatus.
Disclosure of Invention
Therefore, in order to solve the above problems, the present application provides a fault detection method for an air conditioning device, which can detect a system fault before a serious fault occurs in the air conditioning device, and improve the reliability of the air conditioning device.
In a first aspect, the present application provides a fault detection method for an air conditioning device, including:
taking normal equipment operation data as a reference, and comparing the normal equipment operation data with the equipment operation data to be detected to obtain a parameter offset trend of the equipment to be detected, wherein the parameter offset trend comprises an offset direction and an offset degree, and the normal equipment operation data are data of various physical parameters recorded in the operation process of the normal equipment;
and carrying out fault detection on the parameter deviation trend of the equipment to be detected by using rules in an association rule base to obtain a detection result, wherein the association rule base comprises normal rules and abnormal rules.
Further, the operation data refers to data of various physical parameters recorded in the operation process of the air conditioning equipment, such as physical parameters of temperature, pressure, power, rotating speed and the like.
Optionally, in a possible implementation manner of the first aspect of the present application, using a rule in an association rule base to perform fault detection on a parameter offset trend of a device to be detected to obtain a detection result, the method includes:
if the parameter deviation trend of the equipment to be detected accords with the abnormal rule, determining the fault type of the equipment to be detected according to the accorded abnormal rule, and generating a detection result according to the fault type of the equipment to be detected;
if the parameter offset trend of the equipment to be detected does not accord with the abnormal rule but accords with the normal rule, determining that the detection result is that the equipment is normal;
and if the parameter deviation trend of the equipment to be detected does not accord with the abnormal rule and the normal rule, generating a detection result according to the parameter deviation trend of the equipment to be detected which does not accord with the normal rule.
Optionally, in a possible implementation manner of the first aspect of the present application, the normal rule includes a normal association rule and/or a normal expert rule, and the abnormal rule includes an abnormal association rule and/or an abnormal expert rule;
the normal association rule is an association rule which is generated by mining frequent item sets by using an association rule mining algorithm and generating mutual orientation among the screened frequent item sets; the abnormal association rule is obtained by mining a frequent item set by utilizing an association rule mining algorithm and generating an association rule pointing to a fault type from the screened frequent item set, wherein the frequent item set is obtained by performing frequent item mining on a pre-prepared equipment operation data sample;
the normal and abnormal expert rules are normal and abnormal rules generated by manual induction according to expert experience.
Optionally, in a possible implementation manner of the first aspect of the present application, after obtaining the detection result, the method further includes:
submitting the detection result to an expert for confirmation to obtain a confirmation result, wherein the confirmation result is used for indicating whether the detection result is correct or not;
if the confirmation result is false alarm, updating the rule of the association rule base according to the detection result; and if the confirmation result is not false, confirming that the detection result is correct.
Optionally, in a possible implementation manner of the first aspect of the present application, a structural form of the exception association rule is:
{A}→{FT}；
the structural form of the normal association rule is as follows:
{A}→{C}；
wherein, the { A } and the { C } represent frequent item sets formed by parameter deviation trends, the { FT } represents a fault type set, the fault type set comprises at least one fault type, the "→" represents the derivation process of the rule, and the item sets on the left end and the right end are respectively called a front item set and a back item set.
Optionally, in a possible implementation manner of the first aspect of the present application, the normal device is a normal virtual device constructed through software modeling, and accordingly, the normal device operation data is normal virtual operation data obtained through model simulation based on the normal virtual device.
Optionally, in a possible implementation manner of the first aspect of the present application, the method further includes:
acquiring operation data of equipment to be detected and normal equipment operation data;
performing a preprocessing operation on the acquired running data, wherein the preprocessing operation comprises at least one of the following operations: parameter selection, outlier processing, missing value processing, data screening, or pattern classification;
when the preprocessing operation is the mode classification, the preprocessing operation is executed on the acquired running data, and the method comprises the following steps:
dividing the operation state of the air conditioner into at least two operation modes according to the function or the operation state of the air conditioner;
respectively mining rule knowledge under corresponding operation modes aiming at each operation mode of at least two operation modes, wherein the rule knowledge is used for constructing an association rule base;
and mapping the acquired operation data to relevant rules in an association rule base according to the rule knowledge in the operation mode.
In a second aspect, the present application provides a detection apparatus comprising: a comparison module and a detection module;
the comparison module is used for: taking normal equipment operation data as a reference, and comparing the normal equipment operation data with the equipment operation data to be detected to obtain a parameter offset trend of the equipment to be detected, wherein the parameter offset trend comprises an offset direction and an offset degree, and the normal equipment operation data are data of various physical parameters recorded in the operation process of the normal equipment;
the detection module is used for: and carrying out fault detection on the parameter offset trend of the equipment to be detected by using rules in an association rule base to obtain a detection result, wherein the association rule base comprises normal rules and abnormal rules.
In a third aspect, the present application further provides a detection apparatus, including:
a processor and a memory, the memory having stored thereon executable code, which when executed by the processor, causes the detection apparatus to perform the method as described above in the first aspect and any one of its possible implementations.
In a fourth aspect, the present application further provides a computer-readable storage medium having stored thereon executable code, which when executed by a processor of a detection apparatus, causes the detection apparatus to perform the method as described in the first aspect and any one of its possible implementations.
The technical scheme provided by the application has the following beneficial effects at least:
by comparing parameter offset trends between the operation data of the equipment to be detected and normal equipment operation data, including offset direction and offset degree, it can be understood that if the equipment to be detected has a fault, the severity of the fault in the equipment to be detected and the evolution of the fault from slight fault to serious fault can be predicted through the parameter offset trends; finally, the fault can be detected through the normal rule and the abnormal rule in the association rule base to form a detection result, so that the technical scheme of the application can detect the system fault in time before the serious fault of the air conditioning equipment occurs, thereby avoiding causing serious economic loss and improving the reliability of the equipment.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
Fig. 1 is a schematic diagram of an embodiment of a fault detection method for an air conditioning apparatus in an embodiment of the present application;
FIG. 2 is a schematic diagram of a normal association rule determination in an embodiment of the present application;
FIG. 3 is a diagram illustrating abnormal association rule determination in an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a detecting device in an embodiment of the present application;
FIG. 5 is another schematic structural diagram of the detecting device in the embodiment of the present application;
Detailed Description
Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While embodiments of the present application are illustrated in the accompanying drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
The embodiment of the application provides a fault detection method of air conditioning equipment, which is suitable for an air conditioning system, can detect system faults in time before the serious faults of the air conditioning equipment occur, avoids causing serious economic loss, improves the system performance of the air conditioning system, improves the reliability of the equipment, and improves the maintenance efficiency of the equipment, thereby prolonging the service life of the equipment and reducing the use cost.
In order to facilitate understanding of the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application are described in detail below with reference to the accompanying drawings, which are as follows:
fig. 1 is a schematic diagram of an embodiment of a fault detection method for an air conditioning device in the embodiment of the present application.
As shown in fig. 1, a method for detecting a fault of an air conditioning device in an embodiment of the present application includes:
optionally, 101, acquiring operation data of the device to be detected and operation data of the normal device.
In this embodiment of the application, the normal device operation data is data of various physical parameters recorded in the operation process of the normal device, in other words, the operation data refers to data of various physical parameters recorded in the operation process of the air conditioning device, such as physical parameters of temperature, pressure, power, rotation speed, and the like.
Optionally, in an implementation manner of the embodiment of the present application, the normal device is a normal virtual device constructed through software modeling, and accordingly, the normal device operation data is normal virtual operation data obtained through model simulation based on the normal virtual device.
Optionally, in an implementation manner of the embodiment of the present application, after the obtaining the operation parameters in step 101, the method further includes: performing a preprocessing operation on the acquired operation data (including the operation data of the equipment to be detected and the operation data of the reference equipment), wherein the preprocessing operation comprises at least one of the following operations: parameter selection, outlier processing, missing value processing, data screening, or pattern classification.
Further optionally, in an implementation manner of the embodiment of the present application, when the preprocessing operation is the mode classification, the executing the preprocessing operation on the acquired running data includes:
dividing the operation state of the air conditioner into at least two operation modes according to the function or the operation state of the air conditioner;
respectively mining rule knowledge under corresponding operation modes aiming at each operation mode of at least two operation modes, wherein the rule knowledge is used for constructing an association rule base;
and mapping the acquired operation data to relevant rules in an association rule base according to the rule knowledge in the operation mode.
It should be understood that by adopting the preprocessing capability of mode classification, different operation modes use different rules in the association rule base, and the accuracy of the rules can be effectively improved, so that the accuracy of fault detection is improved. It should be further noted that different operation modes are associated with different rules in the association rule base, and it may also be understood that different sub-bases are established in the association rule base, and the rules in different word bases are in one-to-one correspondence with corresponding operation modes, for example, the operation modes include a refrigeration mode and an oil return mode, the refrigeration mode corresponds to the refrigeration rule word base in the association rule base, and similarly, the oil return mode corresponds to the oil return rule sub-base in the association rule base.
Further optionally, in an implementation manner of the embodiment of the present application, if the preprocessing operation is abnormal value processing, the executing of the data preprocessing operation on the to-be-detected device operation data and the reference device operation data includes:
identifying abnormal values in the operation data of the equipment to be detected and the operation data of the reference equipment by using an abnormal value identification method, and replacing the abnormal values with missing values if the abnormal values are continuously smaller than a preset threshold value within a preset time length; and otherwise, deleting the data sample corresponding to the abnormal value, wherein the abnormal value identification method comprises a boxed graph identification method.
Specifically, the abnormal value in the operation parameter data is identified by using a box chart or other abnormal value identification method, the abnormal value is replaced by the missing value if the abnormal value duration is lower than a threshold PT1, and the data sample is directly deleted if the abnormal value duration is not lower than the threshold PT 1.
Further optionally, in an implementation manner of the embodiment of the present application, if the preprocessing operation is missing value processing, the executing of the data preprocessing operation on the to-be-detected device operation data and the reference device operation data includes:
if the sampling time interval between the front and back adjacent samples corresponding to the missing value in the running data of the equipment to be detected and the running data of the reference equipment is less than the preset time length, filling the missing value by using a missing value filling method; and if the sampling time interval is less than the preset time length, deleting the data sample corresponding to the missing value, wherein the missing value filling method comprises a linear interpolation method.
Specifically, for each kind of operation data, if the sampling time difference between the previous sample and the next sample of the missing value or consecutive missing values is lower than the threshold PT2, the missing value is filled by using linear interpolation or other missing value filling methods, and if the sampling time difference is not lower than the threshold PT2, the data sample is directly deleted.
In addition, the preprocessing operation further includes parameter selection and data screening, specifically, the parameter selection is as follows: selecting parameters capable of fully describing the running state of the air conditioning equipment in the collected data, and only reserving independent variable parameters if definite univariate functional relations exist among certain parameters; the data screening is as follows: and screening the stable operation data of the air conditioning equipment by using a moving window method or other stable data judgment methods.
102. And comparing the normal equipment operation data serving as a reference with the equipment operation data to be detected to obtain the parameter offset trend of the equipment to be detected.
In the embodiment of the present application, the parameter offset trend includes an offset direction and an offset degree. Specifically, one or more normal devices are determined by expert analysis or other methods as a reference; and calculating the parameter offset trend of the equipment to be detected relative to the normal equipment, wherein the offset trend comprises the offset direction and the offset degree.
Further, the offset direction may include "greater", "lesser", and "none"; the offset degree can be divided into different degree grades, and can be a non-negative integer such as 0,1,2.
103. And carrying out fault detection on the parameter offset trend of the equipment to be detected by using the rules in the association rule base to obtain a detection result.
In the embodiment of the application, the association rule base comprises a normal rule and an abnormal rule, and is used for judging whether the parameter offset trend of the equipment to be detected is normal or not so as to determine whether the equipment to be detected fails or not. If the parameter deviation of the equipment to be detected is judged to be abnormal through the association rule base, the possibility that the equipment to be detected has faults can be preliminarily judged, and the faults comprise serious faults or slight faults in a sub-health state.
Further specifically, in an implementation manner in the embodiment of the present application, the normal rule includes a normal association rule and/or a normal expert rule, and the abnormal rule includes an abnormal association rule and/or an abnormal expert rule;
the normal association rule is an association rule which is generated by mining frequent item sets by using an association rule mining algorithm and generating mutual orientation among the screened frequent item sets; the abnormal association rule is obtained by mining a frequent item set by utilizing an association rule mining algorithm and generating an association rule pointing to a fault type from the screened frequent item set, wherein the frequent item set is obtained by performing frequent item mining on a pre-prepared equipment operation data sample;
the normal and abnormal expert rules are normal and abnormal rules generated by manual induction based on expert experience, respectively.
Further specifically, optionally, in an implementation manner of the embodiment of the present application, a structural form of the abnormal association rule is:
{A}→{FT}；
the structural form of the normal association rule is as follows:
{A}→{C}；
wherein, the { A } and the { C } represent frequent item sets formed by parameter deviation trends, the { FT } represents a fault type set, the fault type set comprises at least one fault type, the "→" represents the derivation process of the rule, and the item sets on the left end and the right end are respectively called a front item set and a back item set.
Optionally, in an implementation manner of the embodiment of the present application, performing fault detection on a parameter offset trend of a device to be detected by using a rule in an association rule base to obtain a detection result, where the fault detection includes:
if the parameter deviation trend of the equipment to be detected accords with the abnormal rule, determining the fault type of the equipment to be detected according to the accorded abnormal rule, and generating a detection result according to the fault type of the equipment to be detected;
if the parameter offset trend of the equipment to be detected does not accord with the abnormal rule but accords with the normal rule, determining that the detection result is that the equipment is normal;
and if the parameter deviation trend of the equipment to be detected does not accord with the abnormal rule and the normal rule, generating a detection result according to the parameter deviation trend of the equipment to be detected which does not accord with the normal rule.
Optionally, in an implementation manner of the embodiment of the present application, after obtaining the detection result, the method further includes:
submitting the detection result to an expert for confirmation to obtain a confirmation result, wherein the confirmation result is used for indicating whether the detection result is correct or not; if the confirmation result is false alarm, updating the rule of the association rule base according to the detection result; and if the confirmation result is not false, confirming that the detection result is correct.
Specifically, under the condition that the parameter offset trend of the equipment to be detected accords with the abnormal rule, if the result is confirmed to be false alarm, the abnormal rule is updated according to the detection result, wherein the rule updating comprises deleting or modifying the rule; and if the confirmation result is non-false alarm, confirming that the detection result is the equipment fault, and outputting the fault type of the equipment to be detected.
In addition, under the condition that the parameter offset trend of the equipment to be detected does not accord with the abnormal rule or the normal rule, the parameter offset trend of the equipment to be detected which does not accord with the normal rule is determined, and an expert is submitted to confirm the parameter offset trend of the equipment to be detected which does not accord with the normal rule, so that a confirmation result is obtained. Further, the rule update may be performed on the corresponding normal rule according to the confirmation result, where the rule update includes deleting or modifying the rule.
It should be noted that submitting expert confirmation is an expert manual assistance operation for improving accuracy of a detection result, and the expert refers to a professional skilled person in the art. It should be understood that the expert confirmation is submitted for all detection results, including equipment failure or equipment normality, specific fault types in equipment failure, and the like.
In summary, in the technical solution in the embodiment of the present application, by comparing the parameter offset trend between the operation data of the device to be detected and the normal operation data of the device, including the offset direction and the offset degree, it should be understood that if there is a fault in the device to be detected, the severity of the fault in the device to be detected and the evolution of the fault and its change, such as a slight fault to a serious fault, can be predicted through the parameter offset trend; finally, the fault can be detected through the rules in the association rule base to form a detection result, so that the technical scheme of the application can detect the system fault in time before the serious fault of the air conditioning equipment occurs, thereby avoiding serious economic loss and improving the reliability of the air conditioning equipment.
Further, in order to facilitate understanding of the generation process of the parameter offset trend described in the above step 102, the description is further provided.
For convenience of explanation, symbols are defined to represent the parameter shift tendency, PDT is used to represent the parameter shift tendency value, P is used to represent the parameter to be compared ">”、“<"and" ≈ "indicate" large "," small ", and" none "in the offset direction, respectively; l represents the quantized offset degree grade, takes the value of non-negative integers such as 0,1,2. Such as PDT 1 ＝“P 1 >3' denotes P of the apparatus to be investigated 1 Parametric shift trending PDT of parameters 1 Is "P 1 >3”，P 1 The parameter is "large" with respect to the reference device as a whole, and the degree of the deviation is 3 levels.
The parameter offset trend is an overall trend calculated over all the operating data over a given time period, it being understood that the parameter offset trend may be indicative of the course of change of the parameter, and thus the parameter offset trend is the parameter change trend. Alternatively, the overall deviation tendency is calculated using the air conditioner start-up operation data within 1 day as a parameter. The parameter deviation trend can be used for avoiding the range of quantifying specific parameters, converting quantitative variables into qualitative variables and improving the applicability of the association rule. Further, the shorter the time period for running the data, e.g., 1 day, the higher the accuracy.
As a further alternative, the mean and standard deviation of the data are used to describe the overall condition of the data during the period of time, and one method for generating the parameter deviation trend is as follows:
calculating the mean and standard deviation of the parameter P in the reference device in a given time period, respectively denoted as P bl,mean And P bl,std Calculating the mean value P of the parameter P of the equipment to be detected in a given time period wi,mean ；
If (P) bl,mean -k×m 0 ×P bl,std )≤P wi,mean ≤(P bl,mean +k×m 0 ×P bl,std ) If the PDT is equal to 'P ≈ 0';
if (P) bl,mean +k×m L-1 ×P bl,std <P wi,mean ≤P bl,mean +k×m L ×P bl,std Then PDT ═ P>L”；
If P bl,mean -k×m L ×P bl,std ≤P wi,mean <P bl,mean -k×m L-1 ×P bl,std Then PDT＝“P<L”；
Where m is a function of the level L of the degree of offset, i.e. m L F (L), preferably, m is 0.5L +1, L being a non-negative integer such as 0,1,2,. or the like; preferably, k is 2.5; different parameters may have different values for k and m.
And respectively calculating the parameter offset trend values of the parameters for each sample data, and forming a parameter offset trend set.
In order to facilitate understanding of the rules in the association-based rule base described in the above step 103, the following further description specifically includes the following operations described in steps 1 to 5:
step 1: the rules in the association rule base are invoked.
And calling a normal rule set and an abnormal rule set from the established association rule base, wherein the association rule base is constructed in advance, and the association rule base can also be called a rule knowledge base or a parameter trend rule base. The normal rule set is a set of normal association rules and normal expert rules, and the abnormal rule set is a set of abnormal association rules and abnormal expert rules.
Step 2: and judging an abnormal rule, wherein the abnormal rule comprises an abnormal association rule and an abnormal expert rule.
Judging whether the offset trend of each parameter of the equipment to be detected accords with the rule of the abnormal rule set in the rule knowledge base, if so, entering an expert confirmation link, and submitting the fault type output by the rule to an expert for confirmation; if not, entering a normal rule judgment link.
And step 3: and judging normal rules, wherein the normal rules comprise normal association rules and normal expert rules.
Judging whether the deviation trend of each parameter of the equipment to be detected accords with a normal association rule and a normal expert rule in a normal rule set in a rule knowledge base, if so, outputting that the equipment is normal; if the deviation does not meet the requirement, entering an expert confirmation link, and submitting the equipment which does not meet the requirement and the parameter deviation trend to the expert for confirmation.
And 4, step 4: and (5) expert confirmation.
Confirming whether the conclusion of the rule is false, and if the conclusion of the rule is false, updating an association rule base; if the fault type does not belong to the false alarm, outputting the fault or the fault type of the equipment.
And 5: and updating the association rule base.
And updating the rules in the association rule base according to the result confirmed by the expert, and modifying or deleting the rules related to the false alarm.
In addition, the process of constructing the association rule base may specifically include the following operations described in steps 6 to 13:
step 6: and (4) collecting data.
And collecting historical operation data of the air conditioning equipment for mining the normal association rule or the abnormal association rule. In addition, corresponding normal expert rules and abnormal expert rules are generated through manual induction according to expert experience.
And 7: and (4) preprocessing data.
And preprocessing historical operating data, including parameter selection, abnormal value processing, missing value processing, data screening, pattern classification and the like.
And 8: a parameter offset trend is generated.
One or more devices are selected as reference devices, and the deviation trend of the parameters of the device to be detected relative to the reference devices is calculated, wherein the deviation trend comprises the deviation direction and the deviation degree.
And step 9: and (5) frequently mining item sets.
And mining frequent items of the deviation trend in the parameter sample by using an association rule mining algorithm, and forming a frequent item set.
Step 10: and (5) mining association rules.
For the normal association rules, an association rule mining algorithm is used for mining frequent item sets, and association rules which point to each other are generated among the frequent item sets;
and for the abnormal association rule, mining a frequent item set by using an association rule mining algorithm and generating a rule pointing to the fault type from the frequent item set.
Step 11: and (5) constructing an expert rule.
The expert rules include normal expert rules and abnormal expert rules, which are manually defined according to expert experience.
Step 12: and (5) screening the association rules.
And eliminating the normal association rule and the abnormal association rule which do not meet the conditions, and respectively constructing a normal association rule set and an abnormal association rule set.
Step 13: and constructing an association rule base.
And establishing a rule knowledge base, namely an association rule base, by using the screened normal association rule set and the screened abnormal association rule set. In addition, when the association rule base is constructed, the normal expert rules and the abnormal expert rules are respectively added into the normal association rule set and the abnormal association rule set, and the normal expert rule set and the abnormal expert rule set can be respectively created based on the normal expert rules and the abnormal expert rules, so that the application is not limited at all.
In addition, the data required to construct the normal association rule set and the abnormal association rule set should also satisfy certain conditions. The method comprises the following specific steps:
firstly, data required for constructing a normal association rule set should meet the following conditions:
1. the data should include at least one complete operating cycle including data on different operating states of the air conditioning unit, i.e. operating data that substantially covers the user-set mode of operation of the unit and the range of environmental conditions, e.g. 1 full year.
2. The data source can be one or more similar devices, and the similar devices refer to the fact that the structures and functions of parts of the air-conditioning devices are the same, the control logic and software parameters for driving the air-conditioning devices are the same, and the field installation forms of the air-conditioning devices are the same.
Secondly, the data required for constructing the abnormal association rule set should meet the following conditions:
1. the data should contain the operation data of the normal device and the operation data of the fault device, and the normal device and the abnormal device are clear, and the fault type of the fault device is clear.
2. The normal equipment can be fault equipment, the normal equipment data can be operation data before fault of the fault equipment occurs, the normal equipment can also be one or more other similar air-conditioning equipment, the similar means that the parts and the functions of the air-conditioning equipment are the same, the control logic and the software parameters for driving the air-conditioning equipment are the same, and the field installation form of the air-conditioning equipment is the same.
As described in the above step 103, the abnormal association rules and the normal association rules are obtained by mining frequent item sets based on an association rule mining algorithm, where the association rule mining algorithm includes Apriori algorithm, FP-Growth algorithm, and other algorithms for implementing similar functions.
In the section of the generation process described in connection with the parameter offset trend described above: calculating parameter migration trend values of all parameters for each sample data respectively, forming a parameter migration trend set, and mining the frequent item set by using an association rule mining algorithm on the basis of the parameter migration trend set, wherein the following operations can be specifically executed:
taking Apriori algorithm as an example, the Apriori algorithm is utilized to mine a frequent item set in the parameter offset trend set, and support (support) is used as a measurement index of the frequent item set. The support degree is the proportion of the number of times that several (associated) data items appear in the data set to the total data set, or the probability that several (associated) data items occur simultaneously. The support degree is calculated as follows:
where A and C represent a set of data items consisting of parameter offset trends, the set consisting of one or more parameter offset trend values. P (ac) represents the probability of simultaneous occurrence of a and C, number (atoc) represents the number of samples where a and C occur simultaneously, and number (all) represents the total number of samples.
Setting the minimum support threshold as ST, if the support of A and C is greater than or equal to the minimum support threshold ST, then A and C are combined into a frequent item set, which is expressed by { A, C }.
Optionally, ST is 0.05; the ST values of the normal association rule mining and the abnormal association rule may not be the same.
In one aspect, further, the normal association rule mining may perform the following operations:
the structural form of the normal association rule is as follows:
{A}→{C}
in the formula, "→" represents the derivation process of the rule, "→" a on the left end is a preceding term set (antecedent), "→" C on the right end is a following term set (consequent), and the rule means that the occurrence of the C set can be deduced from the occurrence of the a set, and vice versa. For normal association rule mining, the pre-term set and the post-term set are frequent term sets obtained after frequent term set mining operations, i.e., the left end and the right end of a rule are sets composed of one or more parameter offset trends.
Confidence (confidence) and lift (lift) are used as metrics of the normal association rule.
The confidence is defined as:
the definition of the lifting degree is:
and setting the confidence threshold value as CT and the promotion threshold value as LT, and if the confidence of the association rule is greater than or equal to the confidence threshold value CT and the promotion of the association rule is greater than or equal to the promotion threshold value LT, considering that the association rule is effective.
Further, after the normal association rule is obtained by mining, the normal association rule needs to be screened, which is specifically as follows:
specifically, the normal association rule may be filtered according to the following constraint conditions:
a. user setting parameters and environment working condition parameters cannot be located in the rule post-item set, such as setting indoor temperature, setting fan rotating speed, outdoor temperature and the like, and specific limiting parameters are determined according to the type and the function of the air conditioner.
b. According to the known physical law or the air conditioner control logic, rules without connection between the front item set and the rear item set are eliminated, such as a rule "{ inner fan rotating speed >3} → { set temperature <2 }".
c. If there are two rules whose postamble sets are identical and the postamble set of one rule is a subset of the postamble set of the other rule, only the smaller of the postamble sets is retained, as are the two rules "{ PDT 1 }→{PDT 3 } 'and' { PDT 1 ，PDT 2 }→{PDT 3 } ", only the" { PDT "is retained 1 }→{PDT 3 The rule of.
d. If two rules exist, the postfix set of rule 1 is the union of the antefix set and the postfix set of rule 2, then rule 1 is deleted, rule 2 is retained, and at the same time, a rule for deducing the antefix set of rule 2 from the antefix set of rule 1 is generated, if the rule does not exist, then the rule is retained; as two rules "{ PDT 1 }→{PDT 2 } 'and' { PDT 3 }→{PDT 1 ,PDT 2 } ", then" { PDT ] is generated 3 }→{PDT 1 } "and confirm the existence of this rule, delete" { PDT 3 }→{PDT 1 ,PDT 2 And (4) a rule.
e. If a rule exists, the preposition item set of the rule is a union of the preposition item sets of other rules, and the postition item set of the rule is a union of the postition item sets of the rules, deleting the rule; if there are three rules "{ PDT 1 ,PDT 2 }→{PDT 3 ,PDT 4 }”，“{PDT 1 }→{PDT 3 } 'and' { PDT 2 }→{PDT 4 } ", the rule is deleted" { PDT 1 ,PDT 2 }→{PDT 3 ,PDT 4 }”。
f. If two rules exist, the prepositive item set and the postitive item set of the rules are opposite, only the rule with the larger promotion degree is reserved; for example: "{ PDT 1 }→{PDT 2 } 'and' { PDT 2 }→{PDT 1 And } the rule of larger lifting degree is reserved.
The specific judgment by using the normal association rule is as follows: marking the parameter offset trend values in the frequent item set, if all the parameter offset trend values are marked, considering that the air conditioning equipment to be detected accords with a normal association rule set, outputting a judgment conclusion as normal equipment, and if the parameter offset trend is not marked, transferring the equipment and the unmarked parameter offset trend values thereof to an expert confirmation link.
Fig. 2 is a schematic diagram of normal association rule determination in the embodiment of the present application.
As shown in fig. 2, "√" in the figure means that the parameter shift tendency values are marked, if all the parameter shift tendency values are marked, the output device is normal, otherwise the output device fails and an abnormal parameter is output.
In the exemplary case 1 of fig. 2, all the parameter deviation tendency values are marked, and thus the output apparatus is normal, and in the exemplary case 1 of fig. 2, only the PDT 5 Not marked, so that the output device is malfunctioning, and the abnormal parameter is PDT 5 。
On the other hand, further, the abnormal association rule mining may perform the following operations:
the structural form of the abnormal association rule is as follows:
{A}→{FT}
in the formula, A represents a frequent item set formed by parameter offset trends, FT represents a fault type set, and the fault type of fault equipment is already clear before establishing an abnormal association rule. And for abnormal association rule mining, directly deducing the fault type from the frequent item set.
Further, after the abnormal association rule is obtained by mining, the abnormal association rule needs to be screened, which is specifically as follows:
specifically, the normal association rule may be filtered according to the following constraint conditions:
g. the leading item set of the abnormal association rule can not be a normal conclusion of the output equipment after being judged by the normal association rule.
h. And according to the known physical law or the air conditioner control logic, rejecting parameter offset trend values which are not connected with the fault in the front item set.
The specific judgment by using the abnormal association rule is as follows: marking an abnormal association rule preposed item set in the abnormal association rule set, if the preposed item set of a certain abnormal association rule is a subset of a parameter change trend set of target equipment to be detected, outputting and judging the equipment to be failed, wherein the failure type is a failure type deduced by the abnormal association rule and transmitting the failure type to an expert confirmation link; otherwise, the information is transmitted to a normal association rule judgment link.
Fig. 3 is a schematic diagram of abnormal association rule determination in the embodiment of the present application.
As shown in fig. 3, "√" in the figure means that a parameter deviation trend value or a fault type is marked, if all leading entries of an abnormal rule are marked, a fault type mark derived for the abnormal rule, if there is a fault type marked, an output device is in fault, and the fault type is the marked fault type. Specifically, FT2 and FT3 in fig. 3 are labeled, and thus equipment faults are determined and the fault types are FT2 and FT3, where FT represents the fault type.
Specifically, the parameter offset trend values are marked in the following manner, including: associating a rule set flag and a degree of deviation threshold flag;
the association rule set is labeled as: if some parameter deviation trend values completely accord with the preposed item set or the postpositional item set of a certain normal or abnormal association rule, marking the parameter deviation trend values.
The deviation degree threshold is labeled as: if the variation level of some parameter deviation tendency values is less than or equal to the given deviation degree threshold DLT, these parameter deviation tendency values are all marked. Optionally, DLT ═ 1.
Corresponding to the embodiment of the application function implementation method, the application also provides a detection device and a corresponding embodiment.
Fig. 4 is a schematic structural diagram of a detection apparatus in an embodiment of the present application.
As shown in fig. 4, the detecting device 40 in the embodiment of the present application includes:
a comparison module 401 and a detection module 402; (ii) a
The comparison module 401 is configured to: taking the normal equipment operation data as a reference, and comparing the normal equipment operation data with the equipment operation data to be detected to obtain a parameter offset trend of the equipment to be detected, wherein the parameter offset trend comprises an offset direction and an offset degree, and the normal equipment operation data is data of various physical parameters recorded in the normal equipment operation process;
the detection module 402 is configured to: and carrying out fault detection on the parameter offset trend of the equipment to be detected by using rules in an association rule base to obtain a detection result, wherein the association rule base comprises normal rules and abnormal rules.
Further, the operation data refers to data of various physical parameters recorded in the operation process of the air conditioning equipment, such as physical parameters of temperature, pressure, power, rotating speed and the like.
Optionally, in an implementation manner of the embodiment of the present application:
if the parameter offset trend of the equipment to be detected accords with the abnormal rule, the detection module 402 determines the fault type of the equipment to be detected according to the accorded abnormal rule and generates a detection result according to the fault type of the equipment to be detected;
if the parameter offset trend of the equipment to be detected does not accord with the abnormal rule but accords with the normal rule, the detection module 402 determines that the detection result is that the equipment is normal;
if the parameter offset trend of the device to be detected does not conform to the abnormal rule and the normal rule, the detection module 402 generates a detection result according to the parameter offset trend of the device to be detected which does not conform to the normal rule.
Optionally, in an implementation manner of the embodiment of the present application:
the normal rules comprise normal association rules and/or normal expert rules, and the abnormal rules comprise abnormal association rules and/or abnormal expert rules;
the normal association rule is an association rule which is generated by mining frequent item sets by using an association rule mining algorithm and generating mutual orientation among the screened frequent item sets; the abnormal association rule is obtained by mining a frequent item set by using an association rule mining algorithm and generating an association rule pointing to a fault type from the screened frequent item set, wherein the frequent item set is obtained by performing frequent item mining on a device operation data sample prepared in advance;
the normal and abnormal expert rules are normal and abnormal rules generated by manual induction based on expert experience, respectively.
Optionally, in an implementation manner of the embodiment of the present application:
after the detection module 402 obtains the detection result, the detection module 402 submits the detection result to an expert for confirmation to obtain a confirmation result, wherein the confirmation result is used for indicating whether the detection result is correct;
if the determination result is false alarm, the detection module 402 updates the association rule base according to the detection result; if the determination result is not false positive, the detection module 402 determines that the detection result is correct.
Optionally, in an implementation manner of the embodiment of the present application:
the structural form of the abnormal association rule is as follows:
{A}→{FT}；
the structural form of the normal association rule is as follows:
{A}→{C}；
wherein, the { A } and the { C } represent frequent item sets formed by parameter deviation trends, the { FT } represents a fault type set, the fault type set comprises at least one fault type, the "→" represents the derivation process of the rule, and the item sets on the left end and the right end are respectively called a front item set and a back item set.
Optionally, in an implementation manner of the embodiment of the present application:
the normal device is a normal virtual device constructed through software modeling, and correspondingly, the normal device operation data is normal virtual operation data obtained through model simulation based on the normal virtual device.
Optionally, in an implementation manner of the embodiment of the present application:
optionally, as shown in the dotted line in fig. 4, the detecting apparatus 40 further includes an obtaining module 403;
the obtaining module 403 is configured to: acquiring operation data of equipment to be detected and normal equipment operation data;
the obtaining module 403 is further configured to: performing a preprocessing operation on the acquired running data, wherein the preprocessing operation comprises at least one of the following operations: parameter selection, outlier processing, missing value processing, data screening, or pattern classification;
when the preprocessing operation is the mode classification, the obtaining module 403 executes the preprocessing operation on the obtained running data, which specifically includes the following operations:
dividing the operation state of the air conditioner into at least two operation modes according to the function or the operation state of the air conditioner;
respectively mining rule knowledge under corresponding operation modes aiming at each operation mode of at least two operation modes, wherein the rule knowledge is used for constructing an association rule base;
and mapping the acquired operation data to relevant rules in an association rule base according to the rule knowledge in the operation mode.
It should be noted that the obtaining module 403 is an optional module, that is, the detecting apparatus 40 may include two modules, namely, the comparing module 401 and the detecting module 402, and does not include the obtaining module 403; the detection device 40 may also include three modules, namely, a comparison module 401, a detection module 402 and an acquisition module 403.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs operations and the advantages thereof have been described in detail in the embodiment related to the method, and will not be elaborated upon herein.
Fig. 5 is another schematic structural diagram of the detection device in the embodiment of the present application.
As shown in fig. 5, the detection apparatus 50 in the embodiment of the present application includes a memory 501 and a processor 502.
The memory has stored thereon executable code which, when executed by the processor, causes the processor to perform the method of any of the embodiments described above.
The Processor 502 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 501 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions for the processor 502 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, the memory 501 may comprise any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash, programmable read-only memory), magnetic and/or optical disks, may also be employed. In some embodiments, memory 501 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a digital versatile disc read only memory (e.g., DVD-ROM, dual layer DVD-ROM), a Blu-ray disc read only memory, an ultra-dense disc, flash memory cards (e.g., SD, min SD, Micro-SD, etc.), magnetic floppy disks, and the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 501 has stored thereon executable code that, when processed by the processor 502, may cause the processor 502 to perform some or all of the methods described above.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a computer-readable storage medium (or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of a detection apparatus (or an electronic device, a server, etc.), causes the processor to perform part or all of the steps of the above-described method according to the present application.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it should also be noted that, herein, relationships such as first and second, etc., are intended only to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms include, or any other variation is intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. A fault detection method of an air conditioning device is characterized by comprising the following steps:
taking normal equipment operation data as a reference, and comparing the normal equipment operation data with the equipment operation data to be detected to obtain a parameter offset trend of the equipment to be detected, wherein the parameter offset trend comprises an offset direction and an offset degree, and the normal equipment operation data are data of various physical parameters recorded in the operation process of the normal equipment;
and carrying out fault detection on the parameter offset trend of the equipment to be detected by using rules in an association rule base to obtain a detection result, wherein the association rule base comprises normal rules and abnormal rules.
2. The method according to claim 1, wherein the using the rule in the association rule base to perform fault detection on the parameter offset trend of the equipment to be detected to obtain a detection result comprises:
if the parameter deviation trend of the equipment to be detected accords with the abnormal rule, determining the fault type of the equipment to be detected according to the accorded abnormal rule, and generating the detection result according to the fault type of the equipment to be detected;
if the parameter offset trend of the equipment to be detected does not accord with the abnormal rule but accords with the normal rule, determining that the detection result is that the equipment is normal;
and if the parameter deviation trend of the equipment to be detected does not accord with the abnormal rule and the normal rule, generating the detection result according to the parameter deviation trend of the equipment to be detected which does not accord with the normal rule.
3. The method according to claim 1 or 2, wherein the normal rules comprise normal association rules and/or normal expert rules, and the abnormal rules comprise abnormal association rules and/or abnormal expert rules;
the normal association rule is an association rule which is generated by mining frequent item sets by using an association rule mining algorithm and generating mutual orientation among the screened frequent item sets; the abnormal association rule is obtained by mining a frequent item set by using the association rule mining algorithm and generating an association rule pointing to a fault type from the screened frequent item set, wherein the frequent item set is obtained by performing frequent item mining on a device operation data sample prepared in advance;
the normal and abnormal expert rules are normal and abnormal rules generated by manual induction according to expert experience.
4. The method of claim 2, wherein after obtaining the detection result, the method further comprises:
submitting the detection result to an expert for confirmation to obtain a confirmation result, wherein the confirmation result is used for indicating whether the detection result is correct or not;
if the confirmation result is false alarm, updating the rule of the association rule base according to the detection result; and if the confirmation result is not false, confirming that the detection result is correct.
5. The method of claim 4, wherein the abnormal association rule has a structural form of:
{A}→{FT}；
the structural form of the normal association rule is as follows:
{A}→{C}；
wherein { A } and { C } each represent a frequent item set composed of parameter offset trends, { FT } represents a fault type set including at least one fault type, "→" representing a derivation process of the rule, and the item sets on the left and right ends are referred to as a leading item set and a trailing item set, respectively.
6. The method of claim 1, wherein the normal device is a normal virtual device constructed by software modeling, and accordingly, the normal device operation data is based on normal virtual operation data of the normal virtual device obtained by model simulation.
7. The method of claim 1, further comprising:
acquiring the operation data of the equipment to be detected and the operation data of the normal equipment;
performing a preprocessing operation on the acquired running data, wherein the preprocessing operation comprises at least one of the following operations: parameter selection, outlier processing, missing value processing, data screening, or pattern classification;
when the preprocessing operation is the mode classification, the preprocessing operation is executed on the acquired running data, and the preprocessing operation comprises the following steps:
dividing the running state of the air conditioner into at least two running modes according to the function or the running state of the air conditioner;
respectively mining rule knowledge under the corresponding operation mode aiming at each operation mode of the at least two operation modes, wherein the rule knowledge is used for constructing the association rule base;
and mapping the acquired operation data to relevant rules in the association rule base according to the rule knowledge in the operation mode.
8. A detection device, comprising:
a comparison module and a detection module;
the comparison module is used for: taking normal equipment operation data as a reference, and comparing the normal equipment operation data with the equipment operation data to be detected to obtain a parameter offset trend of the equipment to be detected, wherein the parameter offset trend comprises an offset direction and an offset degree, and the normal equipment operation data are data of various physical parameters recorded in the operation process of the normal equipment;
the detection module is used for: and carrying out fault detection on the parameter offset trend of the equipment to be detected by using rules in an association rule base to obtain a detection result, wherein the association rule base comprises normal rules and abnormal rules.
9. A detection device, comprising:
a processor and a memory, the memory having executable code stored thereon;
the executable code, when executed by the processor, causes the detection apparatus to perform the method of any of claims 1-7.
10. A computer readable storage medium having stored thereon executable code which, when executed by a processor of a detection apparatus, causes the detection apparatus to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210757221.8A CN115013936A (en) | 2022-06-30 | 2022-06-30 | Fault detection method and device for air conditioning equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210757221.8A CN115013936A (en) | 2022-06-30 | 2022-06-30 | Fault detection method and device for air conditioning equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115013936A true CN115013936A (en) | 2022-09-06 |
Family
ID=83079794
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210757221.8A Pending CN115013936A (en) | 2022-06-30 | 2022-06-30 | Fault detection method and device for air conditioning equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115013936A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484554A (en) * | 2014-11-26 | 2015-04-01 | 北京航空航天大学 | Method and system for obtaining course correlation degree |
| CN110878983A (en) * | 2019-10-24 | 2020-03-13 | 广州地铁集团有限公司 | Air conditioner fault determination method and device |
| CN111177485A (en) * | 2019-12-16 | 2020-05-19 | 中建材智慧工业科技有限公司 | Method, device and medium for predicting device failure based on parameter rule matching |
| CN111811847A (en) * | 2020-06-08 | 2020-10-23 | 广东寰球智能科技有限公司 | Fault detection method and system for roll-to-roll system and storage medium |
| CN114396705A (en) * | 2021-12-20 | 2022-04-26 | 珠海格力电器股份有限公司 | Air conditioner fault detection method and device, electronic equipment and medium |
-
2022
- 2022-06-30 CN CN202210757221.8A patent/CN115013936A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484554A (en) * | 2014-11-26 | 2015-04-01 | 北京航空航天大学 | Method and system for obtaining course correlation degree |
| CN110878983A (en) * | 2019-10-24 | 2020-03-13 | 广州地铁集团有限公司 | Air conditioner fault determination method and device |
| CN111177485A (en) * | 2019-12-16 | 2020-05-19 | 中建材智慧工业科技有限公司 | Method, device and medium for predicting device failure based on parameter rule matching |
| CN111811847A (en) * | 2020-06-08 | 2020-10-23 | 广东寰球智能科技有限公司 | Fault detection method and system for roll-to-roll system and storage medium |
| CN114396705A (en) * | 2021-12-20 | 2022-04-26 | 珠海格力电器股份有限公司 | Air conditioner fault detection method and device, electronic equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 廖小君、冯先正: "智能变电站信息流的可视化分析与挖掘", 黄河水利出版社, pages: 55 - 58 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11320165B2 (en) | Predictive temperature scheduling for a thermostat using machine learning | |
| CN102667352B (en) | Refrigerant leak detection system and method | |
| JP6351862B2 (en) | Operating state classification device | |
| JP6871877B2 (en) | Information processing equipment, information processing methods and computer programs | |
| CN107391301A (en) | Data managing method, device, computing device and the storage medium of storage system | |
| US11598542B2 (en) | Thermostat scheduling using user devices and machine learning | |
| US11644204B2 (en) | Error correction for predictive schedules for a thermostat | |
| CN111752481B (en) | Memory monitoring and service life prediction method and system based on SPD | |
| CN116432361A (en) | Service life assessment method and device of wind generating set | |
| US11255561B2 (en) | Predictive presence scheduling for a thermostat using machine learning | |
| CN113468157A (en) | Similar building selection method and device based on energy consumption analysis | |
| CN115013936A (en) | Fault detection method and device for air conditioning equipment and storage medium | |
| CN114429249A (en) | Method, system, equipment and storage medium for predicting service life of steel pipe bundle production equipment | |
| CN114528942A (en) | Construction method of data sample library of engineering machinery, failure prediction method and engineering machinery | |
| JP4525414B2 (en) | Abnormality determination apparatus and abnormality determination method | |
| JP2021189552A (en) | Information processing device, information processing method, program, and generation method for learnt model | |
| JP5940018B2 (en) | Data name extraction device and program | |
| JP4461551B2 (en) | Air conditioning load prediction method and apparatus | |
| US20210372647A1 (en) | Method and system for automatic detection of malfunctions/inefficient household electronic heating device | |
| CN113587362A (en) | Abnormity detection method and device and air conditioning system | |
| US11347642B2 (en) | Approach and mechanism for calculating and configuring memory mapping of trend log objects in a system | |
| Leohold et al. | Prognostic Methods for Predictive Maintenance: A generalized Topology | |
| CN114413927B (en) | Lane line fitting method, electronic device and storage medium | |
| WO2021200222A1 (en) | Specification description program and specification description method | |
| WO2023175941A1 (en) | Failure determination system and failure determination method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220906 |
|
| RJ01 | Rejection of invention patent application after publication |