JP7260292B2 - Abnormality diagnosis device and abnormality diagnosis method - Google Patents

Description

TECHNICAL FIELD The present invention relates to a technology of an abnormality diagnosis device and an abnormality diagnosis method for diagnosing an abnormality in equipment.

Systems for diagnosing abnormalities based on operating data have been provided for devices such as air conditioners that are expected to operate constantly. Such anomaly diagnosis is to determine (diagnose) whether the state of the equipment is normal operation or abnormal, and if it is determined to be abnormal as a result, an abnormality is reported. be. Here, the abnormal state indicates a state in which some kind of failure or deterioration has occurred in the device. Such anomaly diagnosis is expected to reduce equipment downtime through early detection of deterioration and failure.

These abnormality diagnoses are performed by detecting the state of the air conditioner with a sensor or the like and using a predetermined diagnostic method based on the detected value of the sensor. Among the various devices to be diagnosed, there are devices that have a wide range of operating conditions depending on the environment in which they are installed, the model of the device, the state of use, and the like. In that case, it may be very difficult to determine whether a change in the measured value of a specific sensor item is due to an abnormality in the device itself or due to a change in operating conditions. In other words, even though there is no abnormality in the equipment itself, it may be diagnosed as "abnormal" due to changes in operating conditions.

For such a problem, for example, Patent Document 1 is disclosed. Patent Literature 1 describes, "The abnormality diagnosis system is an abnormality diagnosis system for diagnosing an abnormality in an air conditioner, and includes a first derivation section, a second derivation section, and an abnormality diagnosis section. The first derivation section The second derivation unit derives a derived value based on the state value regarding the state of the air conditioner at the time of diagnosis.The second derivation unit derives a normal value based on the state value during normal operation of the air conditioner.The abnormality diagnosis unit The derived value and the normal value are tested by statistical processing, and if the derived value and the normal value are considered to have a significant difference, the air conditioner is diagnosed as being in an abnormal state.” An abnormality diagnosis system is disclosed. .

JP-A-2009-002650

However, in the technique described in Patent Literature 1, the operating state classification is created at an early stage. In the technique described in Patent Document 1, only the data of the operating state that conforms to this classification is targeted for diagnosis. For this reason, depending on the sensor data, there is a possibility that it cannot be diagnosed because it does not conform to the classification. Further, in the technique described in Patent Literature 1, a stable state extraction unit extracts data in which the state is stable. Therefore, if the device fails and is not in a stable state, there is a possibility that even data extraction cannot be performed.

The present invention has been made in view of such a background, and an object of the present invention is to improve the accuracy of equipment abnormality diagnosis.

In order to solve the above-described problems, the present invention provides a method in which operating data acquired from equipment is either performance information, which is information derived from the performance of the equipment itself, or operating condition information, which is information relating to the operation of the equipment. and a data type storage unit that stores data type information for determining whether the operating data is a result of learning in advance and for determining whether the operating data is abnormal or normal . and new operation data, which is the newly acquired operation data, are acquired from the device, and based on the learning data, the new operation determined to be abnormal and a learning data addition processing unit that performs processing related to addition of the learning data based on the new driving data if the data is the driving condition information.
Other solutions are described in the embodiments.

ADVANTAGE OF THE INVENTION According to this invention, the precision in abnormality diagnosis of an apparatus can be improved.

It is a figure which shows the structural example of the management system in this embodiment. 1 is a functional block diagram showing a configuration example of an abnormality diagnosis device according to an embodiment; FIG. FIG. 4 is a diagram showing an example of type data stored in a data type storage unit; 4 is a flowchart showing a processing procedure of an abnormality diagnosis method performed in this embodiment;

Next, modes for carrying out the present invention (referred to as "embodiments") will be described in detail with reference to the drawings as appropriate.

[Abnormality diagnosis device 1]
FIG. 1 is a diagram showing a configuration example of a management system Z in this embodiment.
The management system Z has at least one diagnosis target system D, a data terminal 5 installed at the service center C2, and an abnormality diagnosis device 1 installed at the remote monitoring center C1.
Among the diagnostic target systems D, the diagnostic target system Da includes two air conditioners 2 and a control device 3 connected to these air conditioners 2 .
The air conditioner 2 is an object of diagnosis performed by the abnormality diagnosis device 1, and controls indoor air to an arbitrary state. The air conditioner 2 is a multi-air conditioner, an industrial air conditioner for cooling a room in which a computer is housed, or the like.
The air conditioner 2 is provided with a plurality of sensors 201 that detect operating conditions and environmental conditions. These sensors 201 detect state detection values such as the outside air temperature, the room temperature, the frequency of the compressor of the air conditioner 2, the temperature and pressure of the refrigerant circulating inside, the temperature of the refrigerant suction pipe, and the like.

In the diagnosis target system Da, the control device 3 is connected to a plurality of (two in the example of FIG. 1) air conditioners 2 provided in the diagnosis target system Da via communication lines. The control device 3 controls the plurality of air conditioners 2 by setting a set value for control for each air conditioner 2 . Also, the control device 3 is connected to the abnormality diagnosis device 1 via a communication network N. As shown in FIG. Then, the control device 3 transmits the operating data 101 (see FIG. 2) of the air conditioner 2 to the abnormality diagnosis device 1 installed in the remote monitoring center C1. The operation data 101 includes state detection values detected by the sensors 201 of the air conditioners 2, control set values for the air conditioners 2, control details executed by the air conditioners 2, and 2 power consumption, etc. These operating data 101 are detected every predetermined time, for example, every minute. The operating data 101 is continuously or intermittently collected and accumulated by the control device 3 . Then, as described above, the control device 3 transmits the accumulated operating data 101 to the abnormality diagnosis device 1 . Incidentally, in the example of the diagnosis target system Da, the operation data 101 of the two air conditioners 2 are distinguished and transmitted to the abnormality diagnosis device 1 .

Although the diagnosis target system Da is provided with two air conditioners 2, the number may be one or three or more. Further, in the diagnosis target system Da, two air conditioners 2 are connected to one control device 3, but the present invention is not limited to this. For example, the controller 3 may be connected to each air conditioner 2 .

Each of the diagnosis target systems Db and Dc is equipped with a device 4 and a control device 3 . The equipment 4 may be the air conditioner 2 or other equipment 4 . The other devices 4 are devices that are assumed to operate constantly, such as refrigerators, elevators, and plant devices. Alternatively, the device 4 may be configured by connecting one or more devices 4 such as all air conditioning units in a building. Furthermore, the equipment 4 may include other facility equipment such as a hot water supply system and lighting.
Also, the air conditioner 2 of the diagnosis target system Da may be replaced with the device 4 .
In the diagnosis target systems Db and Dc, the device 4 is connected to the control device 3, and the control device 3 transmits the operation data 101 of the device 4 to the abnormality diagnosis device 1 in the same manner as the diagnosis target system Da.

The abnormality diagnosis device 1 is a device that performs abnormality diagnosis of the air conditioners 2 and devices 4 installed in each of a plurality of diagnostic target systems D. FIG. Further, the abnormality diagnosis device 1 is arranged in a remote monitoring center C1 away from the diagnosis target system D in which the air conditioner 2 and the device 4 are arranged. However, the abnormality diagnosis device 1 may be arranged in any one of the diagnosis target systems D. FIG. Thereby, the abnormality diagnosis device 1 remotely monitors the system D to be diagnosed.
The abnormality diagnosis device 1 determines whether the air conditioner 2 is in a normal operating state or an abnormal state from the operation data 101 of the air conditioner 2 and the device 4 sent from the control device 3 . Further, when it is determined that there is an abnormality, the abnormality diagnosis device 1 notifies the administrator of the diagnosis target system D of the abnormality and notifies the data terminal 5 of the service center C2 of the abnormality.

The data terminal 5 that has received the notification of the abnormality notifies the maintenance work of the air conditioner 2 to the serviceman P belonging to the service center C2. The serviceman P who has received the notification is dispatched to perform maintenance work on the diagnosis target system D in which the abnormality has been detected.
The abnormal state here indicates a state in which the air conditioner 2 or the device 4 has some kind of failure or deterioration.

Further, here, it is assumed that the operating data 101 of the air conditioner 2 is transmitted to the abnormality diagnosis device 1 via the communication network N. As shown in FIG. That is, in the example of FIG. 1, the control device 3 is connected to the abnormality diagnosis device 1 via the communication network N. As shown in FIG. However, the control device 3 may be directly connected to the abnormality diagnosis device 1 without the communication network N, that is, in the form of peer-to-peer or VPN (Virtual Private Network).

[Abnormality diagnosis device 1]
FIG. 2 is a functional block diagram showing a configuration example of the abnormality diagnosis device 1 according to this embodiment.
In the following, it is assumed that the device 4 to be diagnosed is the air conditioner 2 .
The abnormality diagnosis device 1 has an input/output vector extraction unit 111 , a learning data selection unit 112 , a regression model generation unit 113 , an abnormality degree calculation unit 114 , a threshold value calculation unit 115 and an abnormality determination unit 116 . Further, the abnormality diagnosis device 1 includes a data type identification unit (learning data addition processing unit) 121, a validity/invalidity determination unit (learning data addition processing unit) 122, a notification unit 123, and a learning data addition unit (learning data addition processing unit) 126. have Further, the abnormality diagnosis device 1 has an evaluation data storage unit 102 , a learning data storage unit 118 , a data type storage unit 124 and an invalid data storage unit (data storage unit) 125 .

Note that the input/output vector extraction unit 111, the learning data selection unit 112, the regression model creation unit 113, the abnormality degree calculation unit 114, the threshold calculation unit 115, the abnormality determination unit 116, and the learning data storage unit 118 are Since the technique is described in the publication, the explanation here is simplified. In the following description, the input/output vector extraction unit 111, the learning data selection unit 112, the regression model creation unit 113, the abnormality degree calculation unit 114, the threshold calculation unit 115, the abnormality determination unit 116, and the learning data storage unit 118 are used for learning and abnormality determination. It may be referred to as section 110 .

The data type identification unit 121, the validity/invalidity determination unit 122, the notification unit 123, the learning data addition unit 126, and the data type storage unit 124 are features of this embodiment. The data type identifying unit 121 , valid/invalid determining unit 122 , reporting unit 123 , learning data adding unit 126 , data type storage unit 124 , and invalid data storage unit 125 are sometimes referred to as additional learning unit 120 .

The input/output vector extraction unit 111 extracts an input vector and an output vector used for the regression model from the operating data 101 output from the air conditioner 2 . The input vector and the output vector are described in Japanese Patent Laid-Open No. 2013-25367, but the input vector is the actual driving data 101 on which the prediction is based, and the output vector is the predicted driving data 101. Note that the output vector may also be the actual operation data 101 as described in Japanese Patent Application Laid-Open No. 2013-25367.
The learning data storage unit 118 accumulates the extracted input vector and output vector as learning data.

The learning data selection unit 112 selects learning data (here, an input vector) from the learning data accumulated in the learning data storage unit 118 based on the degree of similarity with the newly extracted input vector. The newly extracted input vector is stored in the evaluation data storage unit 102, as will be described later.
Regression model creation unit 113 creates a regression model using the selected learning data. For the regression model here, a Gaussian process or the like is used as described in Japanese Patent Application Laid-Open No. 2013-25367.

The degree-of-abnormality calculation unit 114 calculates the degree of abnormality by the method described in Japanese Patent Application Laid-Open No. 2013-25367.
The threshold calculator 115 calculates the threshold described in Japanese Patent Application Laid-Open No. 2013-25367.
The abnormality determination unit 116 determines the operation data 101 by the method described in Japanese Patent Application Laid-Open No. 2013-25367 based on the abnormality degree calculated by the abnormality degree calculation unit 114 and the threshold value calculated by the threshold value calculation unit 115. Abnormal judgment is performed.

The evaluation data stored in the evaluation data storage unit 102 will be described later.

As described above, the learning/abnormality determination unit 110 in this embodiment determines an abnormality in the operation data 101 by using the method described in Japanese Patent Application Laid-Open No. 2013-25367. However, this method is not compatible with the equipment 4, such as the air conditioner 2, in which the operating data 101 is frequently changed. In other words, with the method described in Japanese Patent Application Laid-Open No. 2013-25367, even though there is no abnormality in the air conditioner 2 itself, it may be determined that there is an abnormality simply because the operating data 101 has been changed. Therefore, further improvements are needed. For such improvement, the present embodiment includes an additional learning unit 120 .

The data type storage unit 124 stores type data.
FIG. 3 is a diagram showing an example of type data stored in the data type storage unit 124. As shown in FIG.
As shown in FIG. 3, the type data has fields of "No", "Data Name", "Data Collection Method", and "Type".
"No" is a serial number for each data type.
"Data name" is the name of data such as "outside air temperature" and "intake air temperature".
"Data collection method" indicates how the data was acquired. In the example of FIG. 3, there are "sensor data" and "physical quantity" as the "data collection method". “Sensor data” is raw data obtained from the sensor 201 . A "physical quantity" is calculated by a predetermined formula, a map, or the like based on "sensor data".

"Type" stores information about whether the data is data about "operating conditions" or data about "performance". The "operating condition" is data that changes according to the operating state of the air conditioner 2 and the environment. “Performance” is data derived from the air conditioner 2 itself.
Information about the type of the driving data 101 is created in advance by an administrator or the like and stored in the data type storage unit 124 .

As described above, in the present embodiment, the operating data 101 is provided in advance with type data classified into data indicating "operating conditions" and data indicating "performance". Classifications as shown in FIG. 3 are values almost uniquely determined by the device 4 (here, the air conditioner 2) to be diagnosed. Therefore, if there is general knowledge of the equipment 4, setting is not difficult.

Returning to the description of FIG.
The data type identification unit 121 identifies the type of the operating data 101 determined to be abnormal by the abnormality determination unit 116 .
Validity/invalidity determination section 122 determines whether the abnormality determined by abnormality determination section 116 is valid or invalid based on the type identified by data type identification section 121 . Whether the abnormality is valid or invalid will be described later.
The notification unit 123 notifies the user that an abnormality has occurred when the validity/invalidity determination unit 122 determines that the abnormality is valid.
The invalid data storage unit 125 stores the operation data 101 for which the valid/invalid determination unit 122 determines that the abnormality is “invalid”.
The learning data adding unit 126 adds learning data using the driving data 101 stored in the invalid data storage unit 125 .

The operation data 101 includes state detection values detected by the sensors 201 of the air conditioners 2, control set values for the air conditioners 2, control details executed by the air conditioners 2, and the air conditioners 2. power consumption, etc. Further, as shown in FIG. 3, the operating data 101 includes not only the sensor data of the values detected by the sensor 201, but also physical quantities calculated based on the values detected by the sensor 201.

The abnormality diagnosis device 1 collects learning data for a certain period of time while the device 4 is in the normal state, in order to accumulate input vectors and output vectors as learning data in the learning data storage unit 118 . The state in which the device 4 has no abnormality is a period in which the device 4 has no abnormality, such as a certain period after the device 4 is newly installed. Here, the certain period of time is preferably a period in which the operating conditions assumed for the device 4 to be diagnosed (the air conditioner 2 in the example of this embodiment) appear, but it is not necessary to cover all operating conditions. For example, when the device 4 to be diagnosed is the air conditioner 2, the period during which the operating conditions assumed for the device 4 to be diagnosed appear is the period from the summer setting to the winter setting. Then, the input/output vector extraction unit 111 of the abnormality diagnosis device 1 extracts from the input/output vector extraction unit 111 . The extracted driving data 101 is accumulated in the learning database 6 as learning data.

Further, after the above-described certain period of time has passed, the abnormality diagnosis device 1 stores the acquired operation data 101 in the evaluation data storage unit 102 . The driving data 101 accumulated in the evaluation data storage unit 102 is called evaluation data. When a predetermined amount of evaluation data is accumulated in the evaluation data storage unit 102 , the input/output vector extraction unit 111 extracts input vectors and output vectors from the operation data 101 stored in the evaluation data storage unit 102 . Then, the learning data selection unit 112 selects learning data from the learning data storage unit 118 based on the degree of similarity between the learning data stored in the learning data storage unit 118 and the learning data extracted from the evaluation data. . Note that the learning data here are input vectors.

Further, the abnormality diagnosis device 1 is a PC (Personal Computer) or the like. Programs stored in an HD (Hard Disk) (not shown) or the like are loaded into a memory (not shown) in each of the units 111 to 115, 121 to 123, and 126. FIG. Each unit 111 to 115, 121 to 123, and 126 is realized by executing the loaded program by a CPU (Central Processing Unit) (not shown).

[flowchart]
FIG. 4 is a flow chart showing the processing procedure of the abnormality diagnosis method performed in this embodiment.
Note that FIG. 4 shows the processes after the processing of the abnormality determination unit 116, which is the characteristic part of the present embodiment.
First, abnormality determination processing is performed by the abnormality determination unit 116 (S1).
As a result of the abnormality determination process in step S1, when it is not determined to be abnormal, that is, when it is determined to be normal (S1→normal), the abnormality diagnosis device 1 returns the process to step S1.
If it is determined to be abnormal as a result of the abnormality determination in step S1 (S1→abnormal), the data type identification unit 121 stores the operating data determined to be abnormal based on the type data stored in the data type storage unit 124. 101 type is determined (S2). The type of the operating data 101 is the "type"("operatingcondition","performance") shown in the example of FIG. Information related to "data name" and the like is attached to the operation data 101 acquired from the control device 3 as attribute information.
The fact that the operating data 101 is determined to be abnormal also means that the target operating data 101 is similar to the operating data 101 that greatly affected the calculation of the degree of abnormality.

Based on the result of step S2, the validity/invalidity determination unit 122 determines whether the operational data 101 determined to be abnormal is valid or invalid (S3). Specifically, when the type of the operating data 101 determined to be abnormal is "performance", the validity/invalidity determination unit 122 determines that the abnormality determination is "valid". Further, when the type of the operating data 101 determined to be abnormal is "operating condition", the validity/invalidity determination unit 122 determines that the abnormality determination is "invalid". This is because if the type is "operating condition", it may be determined as abnormal because it is not accumulated as learning data based on the corresponding operating data 101. FIG. Further, when the type of the operation data 101 is "performance", there is a possibility that the device 4 (air conditioner 2) itself is the cause of the abnormality determination, and therefore it is determined to be "effective".

As a result of step S3, when it is determined to be "effective" (S3→"effective"), the notification unit 123 notifies that an abnormality has occurred (S4), and the abnormality diagnosis device 1 returns the process to step S1. For example, information indicating that an abnormality has occurred in the equipment 4 (air conditioner 2) is sent to the display unit (not shown) of the data terminal 5 provided in the service center C2. It is displayed together with the ID of 2). The serviceman P of the service center C2 who received the notification is dispatched to the maintenance work of the device 4 (air conditioner 2) in which the abnormality has occurred.

As a result of step S3, if it is determined to be “invalid” (S3→“invalid”), the valid/invalid determination unit 122 stores the evaluation data (=operation data 101) determined to be “invalid” to the invalid data storage unit 125. (S11). Note that the evaluation data (=operation data 101) stored in the invalid data storage unit 125 is appropriately referred to as invalid data. Also, the input vector and the output vector extracted from the operation data 101 may be stored in the invalid data storage unit 125 . Note that the process of step S11 can be omitted. If the process of step S11 is omitted, the invalid data storage unit 125 can also be omitted.
Then, the learning data addition unit 126 determines whether or not the amount of invalid data has reached a certain amount, for example, at predetermined time intervals (S12). The predetermined time is one week, one month, or the like. Note that step S12 may be a determination as to whether a certain period of time (for example, one week or one month) has elapsed since the previous learning data was added.
As a result of step S12, when the amount of invalid data has not reached a certain amount (S12→No), the abnormality diagnosis device 1 returns the process to step S1.

As a result of step S12, when the amount of invalid data has reached a certain amount (S12→Yes), the learning data addition unit 126 adds the learning data of the learning data storage unit 118 (S13), and the abnormality diagnosis device 1 performs step Return the processing to S1. Specifically, the learning data addition unit 126 extracts an input vector and an output vector from invalid data by the same processing as the input/output vector extraction unit 111 . Then, the learning data adding unit 126 adds the extracted input vector and output vector to the learning data storage unit 118 as learning data.

In the present embodiment, in the processing (S13) by the learning data adding unit 126, the driving data 101 is stored in accordance with the already accumulated learning data, but the present invention is not limited to this. For example, if the learning data to be added has changed significantly from the already stored learning data, the learning data addition unit 126 deletes the already accumulated learning data, and then adds the additional learning data. It may be stored in the learning database 6 . Alternatively, the learning data storage unit 118 may be updated by the method described in JP-A-2013-25367.

The abnormality diagnosis device 1 of this embodiment stores the operation data 101 in the invalid data storage unit 125 when the type of the operation data 101 is the operation condition when an abnormality is determined. As described above, this indicates that there is a possibility that an abnormality has been erroneously determined because the operating conditions are different from those in the past. In other words, it can be said that the abnormality diagnosis device 1 detects changes in operating conditions. That is, the abnormality diagnosis device 1 detects that the operating conditions of the air conditioner 2 to be diagnosed have changed, and accumulates the operating data 101 for adding learning data when the operating conditions change. Thereby, the driving data 101 required for additional learning can be accumulated.

Furthermore, as described above, the abnormality diagnosis device 1 of the present embodiment can add learning data that serves as a reference for abnormality determination as operating conditions change. That is, the abnormality diagnosis device 1 collects learning data for a certain period of time before starting the diagnostic operation, and then starts the actual diagnostic operation.
As a result, it is not always necessary to have learning data for all operating conditions assumed for the equipment 4 to be diagnosed at the start of diagnostic operation. That is, since learning data may be added later, there is no need to collect learning data first over all driving conditions (for example, over four seasons). In other words, the diagnosis can be started after the learning data for judging an abnormality in the operating data 101 is created under some operating conditions, such as only during the summer of the four seasons. Learning data is added when the evaluation data (operating data 101) deviates from the operating conditions. Therefore, the abnormality diagnosis device 1 of the present embodiment can advance the timing at which the abnormality diagnosis can be started. That is, it is possible to shorten the period during which abnormality diagnosis cannot be performed. Further, according to the present embodiment, it is possible to reduce the amount of learning data at the start of diagnostic operation.

Note that in the present embodiment, learning data is added as necessary (when operating conditions change). However, not limited to this, the type of the operation data 101 is almost uniquely determined by the method of the device 4 . Therefore, it is also possible to apply the learning data from the device 4 of the same type that has already started diagnosis to the device 4 that newly starts diagnosis. As a result, it is possible to further advance the timing at which the abnormality diagnosis can be started.
Furthermore, according to the present embodiment, learning data (input vector/output vector) can be added, so the accuracy of abnormality determination can be improved. That is, it is possible to improve the accuracy of predictive diagnosis.

The abnormality diagnosis device 1 of the present embodiment adds learning data that serves as a reference for abnormality diagnosis based on changes in operating conditions as described above. Therefore, at the start of diagnostic operation, even an unknown abnormal state can be diagnosed as an abnormal state as time passes. As a result, even if the user has little knowledge of the equipment 4 to be diagnosed, the abnormality diagnosis can be performed accurately and easily.

Further, in the abnormality diagnosis device 1 of the present embodiment, the types of the operation data 101 are classified in advance, and the type of the acquired operation data 101 is notified only when the type is performance. By doing so, it is possible to prevent erroneous detection of abnormality due to changes in the operating conditions of the device 4 . In other words, in the operating data 101 whose type is the operating condition, it is possible to prevent the device 4 from being determined to be abnormal due to a change in the operating condition, even though the device 4 itself is not originally malfunctioning. By doing so, it is possible to make a more detailed judgment as compared with the case of judging an abnormality simply by setting a threshold for the operation data 101 . As a result, the accuracy of maintenance work can be improved, and the efficiency of maintenance work can be improved.

Further, in the present embodiment, learning data is added after a certain amount of operation data 101 determined to be invalid is accumulated in the invalid data storage unit 125 . By doing so, it is not necessary to always perform additional processing of the learning data, and efficient processing can be performed.

Further, in the present embodiment, the configuration of the learning/abnormality determination unit 110 has the same configuration as described in Japanese Patent Application Laid-Open No. 2013-25367. However, as long as the operation data 101 is learned and the abnormality determination of the operation data 101 is performed based on this learning, the configuration may not be the same as that described in Japanese Patent Application Laid-Open No. 2013-25367.

Furthermore, although this embodiment uses the method described in Japanese Patent Application Laid-Open No. 2013-25367 as a learning method, other machine learning such as clustering may be applied.

The present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above-described embodiments have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the configurations described.

In addition, the configurations, functions, units 110 to 116, 121 to 123, 126, storage units 102, 118, 124 to 125, etc. described above can be partially or entirely designed by, for example, an integrated circuit. It may be implemented in hardware. Further, each configuration, function, etc. described above may be realized by software by a processor such as a CPU (not shown) interpreting and executing a program for realizing each function. Information such as programs, tables, files, etc. that realize each function can be stored in a memory, a recording device such as an SSD (Solid State Drive), an IC (Integrated Circuit) card, or an SD (Secure Digital) card, DVD (Digital Versatile Disc), or other recording medium.

Further, in the present embodiment, the control lines and information lines are those considered to be necessary for explanation, and not necessarily all the control lines and information lines are shown on the product. In fact, it can be considered that almost all configurations are interconnected.

1 abnormality diagnosis device 2 air conditioner 3 control device (equipment)
4 equipment 101 operation data 116 abnormality determination unit 118 learning data storage unit 121 data type identification unit (learning data addition processing unit)
122 valid/invalid determination unit (learning data addition processing unit)
123 reporting unit 124 data type storage unit 125 invalid data storage unit (data storage unit)
126 learning data addition unit (learning data addition processing unit)

Claims (7)

Data type information for determining whether operating data acquired from a device is performance information derived from the performance of the device itself or operating condition information relating to the operation of the device . a stored data type storage unit;
a learning data storage unit that stores learning data that is a result of learning the operating data in advance and that is used to determine whether the operating data is abnormal or normal;
new operating data, which is the newly acquired operating data, is acquired from the device, and if the new operating data determined to be abnormal based on the learning data is the operating condition information, the new operating data; A learning data addition processing unit that performs processing related to adding the learning data based on
An abnormality diagnosis device characterized by comprising: After a predetermined amount of the new operating data determined to be the operating condition information is accumulated in the data storage unit, a process for adding the learning data based on the new operating data determined to be abnormal is performed. The abnormality diagnosis device according to claim 1, characterized by: a notification unit that outputs a notification to the outside when the new operating data is not determined to be the operating condition information, and does not perform the notification to the outside when the new operating data is determined to be the operating condition information; 2. The abnormality diagnosis device according to claim 1, characterized by comprising: The abnormality diagnosis device according to claim 1, wherein the device is an air conditioner. The operating data that is learned first is the operating data that is collected during the period after the equipment is installed until the setting of the equipment switches from a predetermined setting to a setting different from the predetermined setting. The abnormality diagnosis device according to claim 1, characterized by: The learning data addition processing unit
2. The abnormality diagnosis device according to claim 1, wherein when the new operating data is the performance information, no process for adding the learning data based on the new operating data is performed. Data type information for determining whether operating data acquired from a device is performance information derived from the performance of the device itself or operating condition information relating to the operation of the device . a stored data type storage unit;
a learning data storage unit that stores learning data that is a result of learning the operating data in advance and that is used to determine whether the operating data is abnormal or normal;
An abnormality diagnosis device having
acquiring new operating data, which is the newly acquired operating data, from the device;
If the new operating data determined to be abnormal based on the learning data is the operating condition information, a process for adding the learning data based on the new operating data is performed.

Images