CN110531741B - Sensor failure recognition method and storage medium - Google Patents
Sensor failure recognition method and storage medium Download PDFInfo
- Publication number
- CN110531741B CN110531741B CN201910860298.6A CN201910860298A CN110531741B CN 110531741 B CN110531741 B CN 110531741B CN 201910860298 A CN201910860298 A CN 201910860298A CN 110531741 B CN110531741 B CN 110531741B
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- suspected
- fault
- historical
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Abstract
The invention discloses a sensor fault identification method and a storage medium, wherein the method comprises the following steps: receiving data acquired by a sensor in real time, and determining the time characteristic and/or the regional characteristic of the data acquired by the sensor according to the time and/or the place of the data acquired by the sensor; selecting a historical data value range corresponding to the time characteristic and/or the regional characteristic from a sensor historical database; judging whether the data collected by the sensor is in the value range of the historical data: if yes, the sensor is judged to be fault-free; if not, the sensor is judged to be suspected to be faulty; whether the suspected faulty sensor fails or not is further determined according to auxiliary verification data associated with the suspected faulty sensor, and whether the suspected faulty sensor fails or not is further determined according to auxiliary verification data associated with the suspected faulty sensor, so that misjudgment of sensor failure is prevented.
Description
Technical Field
The invention belongs to the technical field of sensor data processing, and particularly relates to a sensor fault identification method and a storage medium.
Background
Along with the improvement of the requirements of people on living level, the intellectualization of the home becomes an important direction for the development of the home in the future. The intelligent home furnishing can not be separated from various sensors, such as a temperature sensor, a photoelectric sensor, a raindrop sensor, a photoelectric sensor, a water immersion sensor, a smoke sensor, a combustible gas sensor, a door and window sensor, a raindrop sensor, a humidity sensor, a human body sensor, a sound sensor and the like.
The sensor is equivalent to human sense for the intelligent home control system, and if the sensor fails, wrong information can be provided for the control system, so that wrong control can be caused. Detection of sensor failure is therefore particularly important.
However, the current sensor directly gives a preset value range when leaving factory, and when a detection value is not in the preset value range, the sensor is judged to have a fault, so that the current sensor has the following problems:
1. the preset value range for judging whether the sensor is in fault is not given according to the actual value of the location of the sensor, so the preset value range is not applicable;
2. when the detection value is not in the preset value range, that is, the sensor is judged to be in fault, the method is too simple, that is, when the detection value is not in the preset value range, the sensor can only be judged to be in fault, and the sensor cannot be directly judged to be in fault.
Therefore, a sensor failure recognition method and a storage medium are needed.
Disclosure of Invention
The invention aims to solve the technical problems that a preset value range given in the existing sensor is not suitable for an actual application scene and the phenomenon of sensor misjudgment caused by too simple sensor fault judgment is avoided.
In order to solve the technical problem, an aspect of the present invention provides a method for constructing a sensor history database, including the following steps:
receiving data collected by a sensor in real time, and determining the time characteristic and/or the regional characteristic of the data collected by the sensor according to the time and/or the place of the data collected by the sensor;
selecting a historical data value range corresponding to the time characteristic and/or the regional characteristic from a sensor historical database;
judging whether the data collected by the sensor is in the value range of the historical data:
if yes, the sensor is judged to be fault-free;
if not, the sensor is judged to be suspected to be faulty;
further determining whether the suspected faulty sensor is faulty based on secondary verification data associated with the suspected faulty sensor.
Preferably, before receiving data collected by a sensor in real time and determining a time characteristic and/or a regional characteristic of the data collected by the sensor according to a time and/or a place of the data collected by the sensor, the method further comprises the following steps:
and constructing a sensor history database.
Preferably, the sensor history database is constructed, and the method specifically comprises the following steps:
grouping the historical data acquired by a sensor according to the time characteristic and/or the regional characteristic of the historical data acquired by the sensor by adopting an autonomous learning method, and determining a value range of the historical data corresponding to the time characteristic and/or the regional characteristic of the historical data according to the grouped historical data;
and storing the historical data, the time characteristics and/or the regional characteristics of the historical data and the historical data value ranges corresponding to the time characteristics and/or the regional characteristics of the historical data to form a sensor historical database.
Preferably, the secondary verification data associated with a suspected faulty sensor comprises at least one of:
a reference value of data collected by a suspected fault sensor;
operating state parameters of the smart home devices associated with the suspected fault sensors; and
data collected by different types of sensors associated with a suspected faulty sensor.
Preferably, the secondary verification data associated with a suspected faulty sensor comprises reference values of data collected by the suspected faulty sensor, said reference values comprising data collected by the same type of sensor contemporaneously within a preset distance range of the suspected faulty sensor or reference data from the network.
Preferably, whether the suspected faulty sensor is faulty is further determined according to the auxiliary verification data associated with the suspected faulty sensor, specifically including the following steps:
judging whether a reference value of data collected by a suspected fault sensor exists or not;
if the reference value of the data collected by the suspected fault sensor exists, judging whether the difference value of the reference value and the data collected by the suspected fault sensor is within a given preset threshold value range:
if the difference value between the reference value and the data collected by the suspected fault sensor is within the range of a preset threshold value, judging that the suspected fault sensor has no fault;
if the difference value between the reference value and the data acquired by the suspected fault sensor is not within the preset threshold range, judging whether the data acquired by the suspected fault sensor is accurate or not according to the running state parameters of the intelligent household equipment associated with the suspected fault sensor and/or the data acquired by different types of sensors associated with the suspected fault sensor:
if so, judging that the suspected fault sensor has no fault;
if not, judging that the suspected fault sensor has a fault,
if the reference value of the data acquired by the suspected fault sensor does not exist, judging whether the data acquired by the suspected fault sensor is accurate or not according to the running state parameters of the intelligent household equipment associated with the suspected fault sensor and/or the data acquired by different types of sensors associated with the suspected fault sensor:
if so, judging that the suspected fault sensor has no fault;
and if not, judging that the suspected fault sensor has a fault.
Preferably, the upper limit value of the preset threshold range is determined according to data collected by the suspected fault sensor.
Preferably, after further determining whether the suspected sensor has a fault and the sensor is determined not to have a fault according to the auxiliary data associated with the suspected faulty sensor, the method further includes:
and storing the data collected by the suspected fault sensor as historical data collected by the sensor into a sensor historical database so as to update the sensor historical database.
Preferably, the data collected by the suspected fault sensor is stored in a sensor history database as history data collected by the sensor to update the sensor history database, and the method specifically includes the following steps:
determining the time characteristic and/or the region characteristic of the data acquired by the sensor according to the time and/or the place of the data acquired by the suspected fault sensor;
selecting a historical data value range corresponding to time characteristics and/or regional characteristics from a sensor historical database;
and adding data acquired by the suspected fault sensor as historical data acquired by the sensor into the value range of the historical data so as to update the value range of the historical data.
According to another aspect of the invention, the invention also provides a storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method as described above.
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
1) by applying the sensor fault identification method, when the data acquired by the sensor is not in the value range of the historical data, only the sensor is judged to be suspected fault, whether the sensor is in fault is further determined according to the auxiliary verification data associated with the suspected fault sensor, the data abnormity caused by the ambient environment factors is eliminated, and the misjudgment of the sensor fault is prevented;
2) by applying the sensor fault identification method, the historical data collected by the sensor are grouped, the historical data value range corresponding to the time characteristic and/or the regional characteristic is determined according to the grouped historical data, the initial fault judgment is performed on the sensor by taking the historical data value range as a judgment reference, and the method is suitable for the actual application scene of the sensor;
3) according to the invention, data which is not in the value range of the historical data and is abnormal due to surrounding environmental factors is stored in the sensor historical database, and the sensor historical database is reconstructed to update the sensor historical database, so that the applicability of the sensor historical database is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a sensor fault identification method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a second sensor fault identification method according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Example one
In order to solve the technical problems in the prior art, the embodiment of the invention provides a sensor fault identification method.
Fig. 1 is a flowchart of a sensor fault identification method according to an embodiment of the present invention. Referring to fig. 1, the method for identifying a sensor fault provided in this embodiment specifically includes the following steps:
s110, grouping the historical data acquired by the sensor according to the time characteristic and/or the regional characteristic of the historical data acquired by the sensor by adopting an autonomous learning method, determining a historical data value range corresponding to the time characteristic and/or the regional characteristic of the historical data according to the grouped historical data, and storing the historical data, the time characteristic and/or the regional characteristic of the historical data and the historical data value range corresponding to the time characteristic and/or the regional characteristic of the historical data to form a sensor historical database;
s120, receiving data collected by a sensor in real time, and determining the time characteristic and/or the regional characteristic of the data collected by the sensor according to the time and/or the place of the data collected by the sensor;
s130, selecting a historical data value range corresponding to the time characteristic and/or the regional characteristic from a sensor historical database;
s140, judging whether the data collected by the sensor is in the value range of the historical data:
if yes, the sensor is judged to be fault-free, and step S180 is executed;
if not, the sensor is judged to be suspected to be faulty, and step S150 is executed;
s150, judging whether reference values of data collected by the suspected fault sensors exist or not:
if yes, go to step S160;
if not, go to step S170;
s160, judging whether the difference value between the reference value and the data collected by the suspected fault sensor is within a given preset threshold range:
if yes, judging that the suspected fault sensor has no fault, and executing step S180;
if not, go to step S170;
s170, judging whether the data acquired by the suspected fault sensor is accurate according to the running state parameters of the intelligent household equipment associated with the suspected fault sensor and/or the data acquired by the different types of sensors associated with the suspected fault sensor:
if yes, judging that the suspected fault sensor has no fault, and executing step S180;
if not, judging that the suspected fault sensor has a fault, and executing the step S190;
s180, storing data collected by the suspected fault sensor and the non-fault sensor into a sensor history database as history data collected by the sensors, and returning to the step S110 to update the sensor history database;
and S190, prompting a user that the suspected fault sensor has a fault.
Example two
In order to solve the above technical problems in the prior art, embodiments of the present invention provide a sensor fault identification method based on the first embodiment, wherein the sensor fault identification method in the first embodiment of the present invention is further improved from step S180 in the first embodiment.
FIG. 2 is a flowchart of a second sensor fault identification method according to an embodiment of the present invention. Referring to fig. 2, the sensor fault identification method of the present embodiment includes the steps of:
s210, grouping the historical data acquired by the sensor according to the time characteristic and/or the regional characteristic of the historical data acquired by the sensor by adopting an autonomous learning method, determining a historical data value range corresponding to the time characteristic and/or the regional characteristic of the historical data according to the grouped historical data, and storing the historical data, the time characteristic and/or the regional characteristic of the historical data and the historical data value range corresponding to the time characteristic and/or the regional characteristic of the historical data to form a sensor historical database;
s220, receiving data collected by a sensor in real time, and determining the time characteristic and/or the regional characteristic of the data collected by the sensor according to the time and/or the place of the data collected by the sensor;
s230, selecting a historical data value range corresponding to the time characteristic and/or the regional characteristic from a sensor historical database;
s240, judging whether the data collected by the sensor is in the value range of the historical data:
if yes, the sensor is determined to be fault-free, and step S281 is executed;
if not, the sensor is determined to be suspected to be faulty, and step S250 is executed;
s250, judging whether reference values of data collected by the suspected fault sensors exist or not, wherein the reference values comprise data collected by the same type of sensors in the same period within a preset distance range of the suspected fault sensors or reference data from a network:
if yes, go to step S260;
if not, go to step S270;
s260, determining whether a difference between the reference value and the data collected by the suspected faulty sensor is within a given preset threshold range, wherein an upper limit of the preset threshold range is determined according to the data collected by the suspected faulty sensor:
if yes, judging that the suspected fault sensor has no fault, and executing step S220;
if not, go to step S270;
s270, judging whether the data acquired by the suspected fault sensor is accurate or not according to the running state parameters of the intelligent household equipment associated with the suspected fault sensor and/or the data acquired by different types of sensors associated with the suspected fault sensor:
if yes, determining that the suspected fault sensor has no fault, and executing step S281;
if not, determining that the suspected fault sensor has a fault, and executing step S290;
s281, determining the time characteristic and/or the region characteristic of the data collected by the sensor according to the time and/or the place of the data collected by the suspected fault sensor and the non-fault sensor;
s282, selecting a historical data value range corresponding to the time characteristic and/or the region characteristic from the sensor historical database;
s283, taking data collected by a suspected fault sensor and a non-fault sensor as historical data collected by the sensors and adding the historical data into the value range of the historical data so as to update the value range of the historical data;
and S290, prompting a user that the suspected fault sensor has a fault.
EXAMPLE III
The present embodiment describes a case where the method of the second embodiment is applied to temperature sensor fault identification.
The temperature sensor fault identification method of the embodiment comprises the following steps:
s310, the temperature sensor collects temperature data in real time, and the rule that the temperature data changes along with time and/or regions is generated by adopting an autonomous learning method, wherein the rule specifically comprises the following three conditions:
first, the law of the temperature data with the change of the region may be as follows: the maximum temperature of the temperature sensor in the first installation place in one year is 35 ℃, and the minimum temperature is 5 ℃; the maximum temperature of the temperature sensor in the second installation place during one year was 42 ℃ and the minimum temperature was 15 ℃.
Second, the temperature data may be time-varying as follows: the highest temperature of the temperature sensor in the first quarter of the year in a fixed installation place is 20 ℃, and the lowest temperature is 5 ℃; the temperature in the first quarter can also be subdivided into a daytime temperature of 20 ℃ at the highest, a temperature of 15 ℃ at the lowest, and a nighttime temperature of 15 ℃ at the highest and a temperature of 5 ℃ at the lowest.
Thirdly, the temperature data change with time and region according to the following rule: the highest temperature of the temperature sensor in the first quarter of the first installation place in the first year is 20 ℃, and the lowest temperature of the temperature sensor is 5 ℃; the temperature sensor has a maximum temperature of 26 ℃ and a minimum temperature of 15 ℃ in the first quarter of the year of the second installation site.
For the three conditions, the historical temperature data collected by the temperature sensor are grouped according to the time characteristic and/or the regional characteristic of the data collected by the sensor, and the value range of the historical temperature data corresponding to the time characteristic and/or the regional characteristic is determined according to the grouped historical temperature data, and the result is as follows:
firstly, the value range of historical temperature data corresponding to a first installation place of the temperature sensor is [5 ℃, 35 ℃; the value range of the historical temperature data corresponding to the temperature sensor in the second installation place is [15 ℃, 42 ℃).
Secondly, the value range of the historical temperature data corresponding to the first quarter of the temperature sensor is [5 ℃ and 20 ℃), the value range of the historical temperature data corresponding to the second quarter of the temperature sensor is [20 ℃ and 30 ℃), the value range of the historical temperature data corresponding to the third quarter of the temperature sensor is [25 ℃ and 35 ℃), and the value range of the historical temperature data corresponding to the fourth quarter of the temperature sensor is [10 ℃ and 20 ℃; the value range of the historical temperature data corresponding to the daytime of the first quarter of the temperature sensor is [15 ℃ and 20 ℃), and the value range of the historical temperature data corresponding to the evening of the first quarter of the temperature sensor is [5 ℃ and 15 ℃).
Thirdly, the value range of the historical temperature data corresponding to the first quarter of the first installation place of the temperature sensor is [5 ℃, 20 ℃), the value range of the historical temperature data corresponding to the second quarter is [20 ℃, 30 ℃), the value range of the historical temperature data corresponding to the third quarter is [25 ℃, 35 ℃), and the value range of the historical temperature data corresponding to the fourth quarter is [10 ℃, 20 ℃; the temperature sensor is arranged in a second installation place, the value range of historical temperature data corresponding to a first quarter is [15 ℃ and 26 ℃), the value range of historical temperature data corresponding to a second quarter is [25 ℃ and 42 ℃), the value range of historical temperature data corresponding to a third quarter is [20 ℃ and 32 ℃), and the value range of historical temperature data corresponding to a fourth quarter is [15 ℃ and 27 ℃).
S320, when the temperature sensor is in the third condition, the temperature collected by the temperature sensor in the first installation place in month 1 is 40 ℃, and the time characteristic of data collection of the temperature sensor is determined to be the first quarter and the regional characteristic is the first installation place;
s330, in the sensor historical database, the value range of historical temperature data corresponding to the temperature sensor in the first quarter of the first installation place is [5 ℃, 20 ℃;
s340, the temperature acquired by the temperature sensor is not within the value range [5 ℃, 20 ℃) of the historical data:
at this time, the temperature sensor is determined to be suspected of malfunctioning, and step S350 is executed;
s350, judging whether other temperature sensors exist in the same room with the suspected fault temperature sensor or not: if yes, collecting the temperature synchronously collected by other temperature sensors, or downloading the local current weather forecast temperature value from the network:
s361, taking the temperature or the weather forecast temperature value synchronously acquired by other temperature sensors as a temperature reference value, and calculating the difference value between the temperature reference value and the temperature acquired by the suspected fault temperature sensor at 40 ℃;
s362, determining whether the difference is within a preset threshold range, for example, within 4 ℃ that is 10% of the temperature collected by the suspected-fault temperature sensor:
if yes, judging that the sensor has no fault, and executing the step S320;
if not, go to step S370;
s370, judging whether the data collected by the suspected fault temperature sensor is accurate at 40 ℃ according to the set temperature of intelligent household equipment such as an air conditioner, an electric heater and the like (intelligent electrical appliances can be networked and can be used for defining an installation room) in the same room with the suspected fault temperature sensor and/or whether the smoke sensor detects smoke;
step S370 includes the following three cases:
firstly, only installing intelligent household equipment such as an air conditioner, an electric heater and the like in the same room of a suspected fault temperature sensor, and at the moment, judging whether data collected by the suspected fault temperature sensor is accurate at 40 ℃ or not through the following steps:
if the set temperature of the air conditioner or the electric heater is within the range of 40 +/-5 ℃, the temperature sensor can be judged to be faultless at the moment, namely the data collected by the suspected fault temperature sensor is accurate at 40 ℃, the temperature collected by the suspected fault temperature sensor is stored into a sensor history database as the history data collected by the sensor, and the step S310 is returned to update the sensor history database;
if the air conditioner or the electric heater is not turned on, the temperature sensor can be judged to be out of order at the moment, and a user is prompted that the sensor is out of order.
Secondly, only a smoke sensor is installed in the same room with the suspected fault temperature sensor, and at the moment, whether the data collected by the suspected fault temperature sensor is accurate at 40 ℃ is judged through the following steps:
if the smoke sensor does not detect smoke, the temperature sensor can be judged to be in fault at the moment, and a user is prompted that the sensor is in fault.
Thirdly, intelligent household equipment such as an air conditioner, an electric heater and the like and a smoke sensor are installed in the same room of the suspected fault temperature sensor, and at the moment, whether the data collected by the suspected fault temperature sensor is accurate at 40 ℃ is judged through the following steps:
if the set temperature of the air conditioner or the electric heater is within the range of 40 +/-5 ℃, the smoke sensor does not detect smoke, the temperature sensor is judged to be faultless at the moment, namely the data collected by the suspected fault temperature sensor is accurate at 40 ℃, the temperature collected by the suspected fault temperature sensor is stored into a sensor history database as the historical data collected by the sensor, specifically, the time characteristic and/or the regional characteristic of the data collected by the sensor, namely the first quarter of a first installation place, are determined according to the time and/or the place of the data collected by the suspected fault temperature sensor, the historical data dereferencing range [5 ℃, 20 ℃) corresponding to the time characteristic and/or the regional characteristic is selected from the sensor history database, the data collected by the suspected fault sensor is added into the historical data dereferencing range [5 ℃, in 20 ℃, the value range of the updated historical data is [5 ℃, 20 ℃) and the set {40 ℃;
if the air conditioner or the electric heater is not turned on, the smoke sensor does not detect smoke, and at the moment, the temperature sensor can be judged to be out of order, and a user is prompted that the sensor is out of order.
In particular, the present embodiment is also applicable to a humidity sensor.
Example four
The present embodiment describes a case where the method of the second embodiment is applied to human body sensor fault identification.
The human body sensor fault identification method of the embodiment comprises the following steps:
s410, the human body sensor collects the time point of human body appearance in real time, and an autonomous learning method is adopted to generate the rule that the time point of human body appearance changes along with time and/or region, wherein the rule specifically comprises the following three conditions:
first, the law that the time point when the human body appears varies with the region may be as follows: the time points of the human body sensors at which the human body appears at the first installation site are 5:30, 5:33, 5:45, 6:18, 6:35, 7:28, 8:01, 9:10, 8:01, 18:25, 18:11, 18:25, 18:45, 19:53, 19:11, 20:15, 21: 45; the time points at which the body sensor appears in the second installation site are 6:50, 7:13, 7:25, 6:18, 7:01, 10:01, 9:01, 7:48, 20:33, 20:11, 20:25, 20:45, 22:13, 21: 21.
Secondly, the time point of human appearance may change with time as follows: the time points of the human body sensors when the human body appears on the working day of the fixed installation are 5:30, 5:33, 5:45, 6:18, 6:35, 18:25, 18:11, 18:25, 18:45, 19:53 and 19: 11; the time points of the appearance of the human body in holidays are 7:28, 8:01, 9:10, 8:01, 20:15 and 21: 45.
Thirdly, the time point of the human body changes with time and regions according to the following rule: the human body sensors are arranged at the time points of human bodies appearing on working days of the first installation place, namely 5:30, 5:33, 5:45, 6:18, 6:35, 18:25, 18:11, 18:25, 18:45, 19:53 and 19:11, and at the time points of human bodies appearing on holidays, namely 7:28, 8:01, 9:10, 8:01, 20:15 and 21: 45; the human body sensors are 6:50, 7:13, 7:25, 6:18, 7:01, 7:48, 20:33, 20:11, 20:25 and 20:45 at the time points of appearance of human bodies on the working day of the second installation place, and are 10:01, 9:01, 22:13 and 21:21 at the time points of appearance of human bodies on holidays.
For the three conditions, the historical time points of the human body, which are acquired by the human body sensor, appearing are grouped according to the time characteristic and/or the regional characteristic of the data acquired by the sensor, and the value range of the historical time points of the human body, which correspond to the time characteristic and/or the regional characteristic, appearing is determined according to the grouped historical time points of the human body, and the result is as follows:
firstly, the value ranges of the historical time points of the human body corresponding to a first installation place are [5:30, 9:10] and [18:11, 21:45 ]; the values of the historical time points of the human body corresponding to the second installation place of the human body sensor are [6:18, 10:01] and [20:11, 22:13 ].
Secondly, the value ranges of the historical time points of the human body appearance corresponding to the working day of the human body sensor are [5:30, 6:35] and [18:11, 19:53], and the value ranges of the historical time points of the human body appearance corresponding to the holidays of the human body sensor are [7:28, 9:01] and [20:15, 21:45 ].
Thirdly, the value ranges of the historical time points of the human body appearance corresponding to the working days of the first installation place are [5:30, 6:35] and [18:11, 19:53], and the value ranges of the historical time points of the human body appearance corresponding to holidays are [7:28, 9:01] and [20:15, 21:45 ]; the values of the historical time points of the human bodies corresponding to the working days of the second installation place are [6:18, 7:48] and [20:11, 20:45], and the values of the historical time points of the human bodies corresponding to the holidays are [9:01, 10:01] and [21:21, 22:13 ].
S420, when the human body sensor is in the third condition, if the time of the human body sensor collecting the human body in 2019, 7, 15 and 30 days in the first installation place is 20:30, determining that the time characteristic of data collection of the human body sensor is a working day and the regional characteristic is the first installation place;
s430, the value ranges of the historical time points of the human body appearance corresponding to the working days of the first installation place of the human body sensor are [5:30, 6:35] and [18:11, 19:53 ];
s440, the time 20:30 when the human body sensor collects the appearance of the human body is not in the value range [5:30, 6:35] or [18:11, 19:53] of the historical time point:
at this time, the human body sensor is determined as a suspected fault, and step S450 is executed;
s450, judging whether other human body sensors exist in the same room with the suspected fault human body sensor or not: if yes, collecting the time points of the human body which are synchronously collected by other human body sensors; if not, go to step S470;
s461, taking the time points of the human bodies which are synchronously collected by other human body sensors as time reference values, and calculating the difference value between the time reference values and the time points 20:30 which are collected by the suspected fault human body sensors;
s462, determining whether the difference is within a preset threshold range, for example, 10 minutes:
if yes, judging that the sensor has no fault, and executing step S420;
if not, go to step S470;
s470, judging whether the time point 20:30 acquired by the suspected fault human body sensor is accurate or not according to the working state of intelligent household equipment such as an intelligent door lock and the like (intelligent electrical appliances can be networked and can define and install a room) in the same room with the suspected fault human body sensor;
if the intelligent door lock is normally opened, judging that the sensor is not in fault, and executing the step S480;
if the intelligent door lock is not opened, judging that the sensor has a fault, and executing the step S490;
if the intelligent door lock is forced to open the door, the intelligent door lock is judged to be illegally accessed;
s480, storing the time point 20:30 acquired by the suspected fault human body sensor into a sensor history database as historical data acquired by the human body sensor, specifically, determining the time characteristic and/or the regional characteristic of the data acquired by the sensor, namely the first installation place working day, according to the time and/or the place of the data acquired by the suspected fault temperature sensor, selecting the historical data value range [5:30, 6:35] and [18:11, 19:53] corresponding to the time characteristic and/or the regional characteristic from the sensor history database, adding the data acquired by the suspected fault sensor as the historical data acquired by the sensor into the historical data value range [18:11, 19:53] to update the historical data value range [18:11, 19:53] and the set {20:30 };
and S490, prompting the user that the sensor is out of order.
EXAMPLE five
In order to solve the above technical problems in the prior art, an embodiment of the present invention further provides a storage medium.
The storage medium of the present embodiment has stored thereon a computer program which, when executed by a processor, implements the steps of the sensor failure identification method described above.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A sensor fault identification method is characterized by comprising the following steps:
receiving data collected by a sensor in real time, and determining the time characteristic and/or the regional characteristic of the data collected by the sensor according to the time and/or the place of the data collected by the sensor;
selecting a historical data value range corresponding to the time characteristic and/or the regional characteristic from a sensor historical database;
judging whether the data collected by the sensor is in the value range of the historical data:
if yes, the sensor is judged to be fault-free;
if not, the sensor is judged to be suspected to be faulty;
further determining whether the suspected faulty sensor is faulty based on secondary verification data associated with the suspected faulty sensor;
the auxiliary verification data comprises at least one of reference values of data collected by suspected fault sensors, operation state parameters of smart home equipment associated with the suspected fault sensors and data collected by different types of sensors associated with the suspected fault sensors.
2. The method of claim 1, further comprising the steps of, before receiving the data collected by the sensor in real time and determining the time characteristics and/or the regional characteristics of the data collected by the sensor according to the time and/or the location of the data collected by the sensor: and constructing a sensor history database.
3. The method of claim 2, wherein constructing the sensor history database comprises the steps of:
grouping the historical data acquired by a sensor according to the time characteristic and/or the regional characteristic of the historical data acquired by the sensor by adopting an autonomous learning method, and determining a value range of the historical data corresponding to the time characteristic and/or the regional characteristic of the historical data according to the grouped historical data;
and storing the historical data, the time characteristics and/or the regional characteristics of the historical data and the historical data value ranges corresponding to the time characteristics and/or the regional characteristics of the historical data to form a sensor historical database.
4. The method of claim 1, wherein the reference value comprises data collected simultaneously by sensors of the same type within a preset distance range of a suspected faulty sensor or reference data from a network.
5. The method of claim 1, wherein determining whether the suspected faulty sensor is faulty is further based on secondary verification data associated with the suspected faulty sensor, comprising:
judging whether reference values of data collected by a suspected fault sensor exist or not:
if the reference value of the data collected by the suspected fault sensor exists, judging whether the difference value of the reference value and the data collected by the suspected fault sensor is within a given preset threshold value range:
if the difference value between the reference value and the data collected by the suspected fault sensor is within the range of a preset threshold value, judging that the suspected fault sensor has no fault;
if the difference value between the reference value and the data acquired by the suspected fault sensor is not within the preset threshold range, judging whether the data acquired by the suspected fault sensor is accurate or not according to the running state parameters of the intelligent household equipment associated with the suspected fault sensor and/or the data acquired by different types of sensors associated with the suspected fault sensor:
if so, judging that the suspected fault sensor has no fault;
if not, judging that the suspected fault sensor has a fault;
if the reference value of the data acquired by the suspected fault sensor does not exist, judging whether the data acquired by the suspected fault sensor is accurate or not according to the running state parameters of the intelligent household equipment associated with the suspected fault sensor and/or the data acquired by different types of sensors associated with the suspected fault sensor:
if so, judging that the suspected fault sensor has no fault;
and if not, judging that the suspected fault sensor has a fault.
6. The method of claim 5, wherein the upper limit of the preset threshold range is determined based on data collected by a suspected faulty sensor.
7. The method of claim 1, further comprising, after further determining whether the suspected faulty sensor is faulty and the sensor is determined to be non-faulty based on the aiding data associated with the suspected faulty sensor:
and storing the data collected by the suspected fault sensor as historical data collected by the sensor into a sensor historical database so as to update the sensor historical database.
8. The method according to claim 7, wherein the step of storing the data collected by the suspected fault sensor as historical data collected by the sensor in a sensor historical database to update the sensor historical database comprises the steps of:
determining the time characteristic and/or the region characteristic of the data acquired by the sensor according to the time and/or the place of the data acquired by the suspected fault sensor;
selecting a historical data value range corresponding to time characteristics and/or regional characteristics from a sensor historical database;
and adding data acquired by the suspected fault sensor as historical data acquired by the sensor into the value range of the historical data so as to update the value range of the historical data.
9. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910860298.6A CN110531741B (en) | 2019-09-11 | 2019-09-11 | Sensor failure recognition method and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910860298.6A CN110531741B (en) | 2019-09-11 | 2019-09-11 | Sensor failure recognition method and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110531741A CN110531741A (en) | 2019-12-03 |
| CN110531741B true CN110531741B (en) | 2020-11-27 |
Family
ID=68668431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910860298.6A Active CN110531741B (en) | 2019-09-11 | 2019-09-11 | Sensor failure recognition method and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110531741B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111475384B (en) * | 2020-05-07 | 2022-12-20 | Oppo广东移动通信有限公司 | Shell temperature calculation method and device, storage medium and electronic equipment |
| CN115834351A (en) * | 2023-02-23 | 2023-03-21 | 国网浙江义乌市供电有限公司 | Fault judgment method for sensing acquisition equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105425775A (en) * | 2015-12-04 | 2016-03-23 | 河南中烟工业有限责任公司许昌卷烟厂 | Sensor fault automatic judgment method and system |
| CN106289363A (en) * | 2016-08-01 | 2017-01-04 | 长沙理工大学 | A kind of interference environment sensor fault judge mark method |
| JP2017190482A (en) * | 2016-04-12 | 2017-10-19 | 株式会社神戸製鋼所 | System for detecting failure of blast furnace sensor and system for predicting abnormal condition of blast furnace |
| CN109688602A (en) * | 2019-02-28 | 2019-04-26 | 福建师范大学 | Wireless sensor fault detection algorithm based on node pre-state |
| US10354196B2 (en) * | 2016-12-16 | 2019-07-16 | Palantir Technologies Inc. | Machine fault modelling |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108600704A (en) * | 2018-05-08 | 2018-09-28 | 深圳市智汇牛科技有限公司 | A kind of monitoring system framework in automatic kitchen field |
-
2019
- 2019-09-11 CN CN201910860298.6A patent/CN110531741B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105425775A (en) * | 2015-12-04 | 2016-03-23 | 河南中烟工业有限责任公司许昌卷烟厂 | Sensor fault automatic judgment method and system |
| JP2017190482A (en) * | 2016-04-12 | 2017-10-19 | 株式会社神戸製鋼所 | System for detecting failure of blast furnace sensor and system for predicting abnormal condition of blast furnace |
| CN106289363A (en) * | 2016-08-01 | 2017-01-04 | 长沙理工大学 | A kind of interference environment sensor fault judge mark method |
| US10354196B2 (en) * | 2016-12-16 | 2019-07-16 | Palantir Technologies Inc. | Machine fault modelling |
| CN109688602A (en) * | 2019-02-28 | 2019-04-26 | 福建师范大学 | Wireless sensor fault detection algorithm based on node pre-state |
Non-Patent Citations (2)
| Title |
|---|
| 基于数据特征的多线传感器故障诊断;邓方;《第二十九届中国控制会议论文集》;20100731;第3889-3894页 * |
| 基于模糊动态模型的传感器故障诊断方法;黄孝彬;《中 国 电 机 工 程 学 报》;20030331;第23卷(第3期);第183-187页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110531741A (en) | 2019-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110531741B (en) | Sensor failure recognition method and storage medium | |
| CN106841928B (en) | Power distribution network fault section positioning method and system based on multi-source information fusion | |
| CN111578444A (en) | Air conditioner fault prediction method and device, storage medium and air conditioner | |
| WO2016135514A1 (en) | Method and apparatus for controlling an environment management system within a building | |
| CN111400758B (en) | Access right verification method, device and system applied to Internet of things | |
| CN107604590B (en) | Control method, control device and control system of washing machine based on Internet of things | |
| Xiao et al. | Cooling load disaggregation using a NILM method based on random forest for smart buildings | |
| CN112556130A (en) | Air conditioner alarm control method and device, electronic equipment and storage medium | |
| CN106249835A (en) | The method being applicable to power management, system, user terminal and device | |
| CN113359502A (en) | Intelligent home multi-sensor detection method and system based on artificial intelligence and storage medium | |
| CN109697304A (en) | A kind of construction method of refrigeration unit multi-sensor data prediction model | |
| Andersson | Modeling electricity load curves with hidden Markov models for demand‐side management status estimation | |
| CN112034727A (en) | Smart scene-based home equipment management method and smart home control device | |
| Howard et al. | Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data | |
| CN113298175B (en) | Method and system for monitoring power consumption of solitary old people based on multiple scenes and multiple data | |
| JP4461551B2 (en) | Air conditioning load prediction method and apparatus | |
| CN110889465B (en) | Power demand side equipment identification method and system based on self-adaptive resonant network | |
| CN114251812A (en) | Parameter setting method and device of air conditioner and air conditioner | |
| JP2001245432A (en) | Device for demand forecast | |
| CN112733456A (en) | Electricity stealing prevention behavior identification method and system | |
| EP3111177A1 (en) | A method of detecting a defect light sensor | |
| CN113627451A (en) | Non-invasive household electricity consumption behavior dynamic monitoring method based on Bayesian network | |
| Perić et al. | Prediction of User-defined Room Temperature Setpoints by LSTM Neural Networks | |
| Guo et al. | Fault detection and diagnosis for residential hvac systems using transient cloud-based thermostat data | |
| CN113864981B (en) | Control method and device for fresh air of air conditioner and processor |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |