CN104075749A - Abnormal state detecting method and system for equipment in internet of things - Google Patents
Abnormal state detecting method and system for equipment in internet of things Download PDFInfo
- Publication number
- CN104075749A CN104075749A CN201410305059.1A CN201410305059A CN104075749A CN 104075749 A CN104075749 A CN 104075749A CN 201410305059 A CN201410305059 A CN 201410305059A CN 104075749 A CN104075749 A CN 104075749A
- Authority
- CN
- China
- Prior art keywords
- equipment
- state
- detection
- unit exception
- internet
- 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
Landscapes
- Telephonic Communication Services (AREA)
Abstract
The invention discloses an abnormal state detecting method and system for equipment in the internet of things. The method comprises the following steps of receiving equipment operation state detection information, analyzing the detection information, obtaining equipment states of the equipment, judging whether the similarity between the equipment states and any stored equipment state in state space is in a preset range, judging that the equipment is in normal operation if the similarity is in the preset range and giving out virtual alarm information that the equipment may be abnormal if the similarity is not in the preset range. According to the abnormal state detecting method and system, the equipment operation states are judged by taking factors into consideration instead of only relying on read values of a sensor. Thus, the abnormal state detecting method and system are accurate in judgment. Furthermore, a plurality of normal operation states are previously stored, the current equipment operation states are compared with the normal operation states, and the false alarm ratio is effectively reduced.
Description
Technical field
The present invention relates to Internet of Things field, relate in particular to the method and system of unit exception state-detection in a kind of Internet of Things.
Background technology
Industry Internet of Things, by having all kinds of collections of perception, monitoring capacity or controlling sensing or the technology such as controller and ubiquitous technology, mobile communication, intellectual analysis is constantly dissolved into industrial processes links, is realized the target that traditional industry is risen to the intelligentized new stage.From application form, the application of industrial Internet of Things has the features such as real-time, robotization, embedded (software), security and information mutual communication interconnectivity.
The comparison in equipment relating in Internet of Things is many, conventionally need to monitor the running status of equipment, so that the misoperation of discovering device in time.In conventional art, most of dcss (Distributed Control System, DCS) when carrying out monitoring of tools, the value of reading of too much dependence device sensor whether go beyond the scope (threshold value) weigh the state of commercial unit or production.Yet, actual production process is affected by many factor of productions, and in process of production, the device fabrication state variation causing due to the adjustment demand of production capacity goes beyond the scope the device sensor value of reading, be not easily distinguishable with the state variation causing due to equipment failure, very easily cause alarm frequently and wrong report.
Summary of the invention
Based on this, be necessary, for the simple value of the reading judgment device running status that relies on device sensor in conventional art, easily to cause the problem of wrong report, the method and system of unit exception state-detection in the Internet of Things that a kind of rate of false alarm is low are provided.
For realizing the method for unit exception state-detection in a kind of Internet of Things that the object of the invention provides, comprise the following steps:
The detection information of receiving equipment running status, and described detection information is analyzed, the equipment state of described equipment obtained;
Judge that arbitrary similarity between storage device status in described equipment state and state space is whether in preset range;
If so, determining apparatus is normally moved;
If not, send the false alarming information that equipment may be abnormal.
As the embodiment of a kind of method of unit exception state-detection in Internet of Things, step is if not, after the false alarming information that the equipment that sends may be abnormal, further comprising the steps of:
Wait for the confirmation of user to described false alarming information;
When receiving the described false alarming information of the confirmation corresponding device abnormal operating condition of user's input, send unit exception and report to the police;
When receiving the described false alarming information of the confirmation corresponding device normal operating condition of user's input, described equipment state is stored in described state space.
As the embodiment of a kind of method of unit exception state-detection in Internet of Things, described described equipment state is stored in described state space after, further comprising the steps of:
Whether the quantity that judges the described equipment state of storing in described state space is greater than preset value;
If so, adopt the method for incremental clustering to optimize described state space;
If not, finish this unit exception state-detection.
As the embodiment of a kind of method of unit exception state-detection in Internet of Things, the detection information exchange of described equipment running status is crossed the sensor being connected with described equipment and is obtained.
As the embodiment of a kind of method of unit exception state-detection in Internet of Things, described described detection information is analyzed, obtain the equipment state of described equipment, comprise the following steps:
Time window with predetermined width intercepts described detection information;
The slope of the described detection information in the predetermined width that matching intercepts;
The number of described slope equates with the test item number that described detection information comprises;
The described equipment state vector that described slope forms of serving as reasons;
Described storage device status is pre-stored default vector.
As the embodiment of a kind of method of unit exception state-detection in Internet of Things, judge that arbitrary similarity between storage device status in described equipment state and state space whether in preset range, comprises the following steps:
Cosine angle between the vector of computing equipment state and all described default vector;
Whether the minimum described cosine angle of judgement is less than default angle;
If so, described similarity in preset range;
If not, described similarity not in preset range.
As the embodiment of a kind of method of unit exception state-detection in Internet of Things, the method for described employing incremental clustering is optimized described state space, comprises the following steps:
Increase the preset range of described similarity to the first preset range;
Similarity is merged into a new equipment state in the equipment state of having stored described in two of described the first preset range, and store in described state space;
Described the first preset range in the circulation of next unit exception state-detection as new preset range.
The system of unit exception state-detection in a kind of Internet of Things based on identical inventive concept, comprises information receiving and analyzing module, the first judge module, the first execution module and the second execution module, wherein:
Described information receiving and analyzing module, for the detection information of receiving equipment running status, and analyzes described detection information, obtains the equipment state of described equipment;
Described the first judge module, for arbitrary similarity between storage device status of judging described equipment state that described information receiving and analyzing module generates and state space whether in preset range;
Described the first execution module, for according to the judged result of described the first judge module, when described similarity is in described preset range, determining apparatus is normally moved, and waits the unit exception of pending next circulation to detect;
Described the second execution module, for according to the judged result of described the first judge module, when described similarity is not in described preset range, sends the false alarming information that equipment may be abnormal.
As the embodiment of the system of unit exception state-detection in a kind of Internet of Things, also comprise alarm module and storage execution module, wherein:
Described alarm module, for when receiving the described false alarming information of the confirmation corresponding device abnormal operating condition of user's input, sends unit exception and reports to the police;
Described storage execution module, for when receiving the described false alarming information of the confirmation corresponding device normal operating condition of user's input, stores described equipment state in described state space into.
As the embodiment of the system of unit exception state-detection in a kind of Internet of Things, also comprise the second judge module, the 3rd execution module and the 4th execution module, wherein:
Described the second judge module, for judging whether the quantity of the described equipment state that described state space is stored is greater than preset value;
Described the 3rd execution module, for according to the judged result of described the second judge module, when being greater than preset value, adopts the method for incremental clustering to optimize described state space;
Described the 4th execution module, for according to the judged result of described the second judge module, when being less than or equal to preset value, finishes this unit exception state-detection.
As the embodiment of the system of unit exception state-detection in a kind of Internet of Things, also comprise the sensor of connection device, described information receiving and analyzing module receives the detection information of the described equipment running status of described sensor feedback.
Beneficial effect of the present invention comprises:
The method and system of unit exception state-detection in a kind of Internet of Things provided by the invention, a plurality of detection information structure equipment states of package, and equipment state and the state of the normal operation of the equipment prestoring are compared.If running status and default running status difference are very large, sending may be the false alarming information of misoperation, reminds related personnel to confirm to process.If equipment running status is little with respect to the running status difference of having stored in state space, think equipment normal operation.To the comprehensive a plurality of factors of the judgement of equipment running status, do not rely on merely the value of reading of sensor, accuracy of judgement, and pre-stored a plurality of normal operating condition, the running status that equipment is current and each normal operating condition compare, and can effectively reduce rate of false alarm.The accuracy rate that more provides unit exception to report to the police can be constantly provided state space along with detecting the increase of number of times simultaneously.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a specific embodiment of the method for unit exception state-detection in a kind of Internet of Things of the present invention;
Fig. 2 is the process flow diagram of another specific embodiment of the method for unit exception state-detection in a kind of Internet of Things of the present invention;
Fig. 3 is the process flow diagram of a specific embodiment again of the method for unit exception state-detection in a kind of Internet of Things of the present invention;
Fig. 4 is the time window schematic diagram of the method for unit exception state-detection in a kind of Internet of Things of the present invention;
Fig. 5 a-5d is the schematic diagram that the equipment state of a specific embodiment of the method for unit exception state-detection in a kind of Internet of Things of the present invention adds state space;
Fig. 6 is that the different time window of an instantiation detects design sketch;
Fig. 7 is the aggregation number schematic diagram of the different conditions space memory space of an instantiation;
Fig. 8 is the formation schematic diagram of a specific embodiment of the system of unit exception state-detection in a kind of Internet of Things of the present invention;
Fig. 9 is the formation schematic diagram of another specific embodiment of the system of unit exception state-detection in a kind of Internet of Things of the present invention;
Figure 10 is the formation schematic diagram of a specific embodiment again of the system of unit exception state-detection in a kind of Internet of Things of the present invention.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with accompanying drawing, the embodiment of the method and system of unit exception state-detection in Internet of Things of the present invention is described.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
The method of unit exception state-detection in the Internet of Things of one embodiment of the invention, as shown in Figure 1, comprises the following steps:
S100, the detection information of receiving equipment running status, and described detection information is analyzed, obtain the equipment state of described equipment.
The running state information of the sensor checkout equipment that can be with by internet of things equipment self also can be installed corresponding sensor as required on internet of things equipment, as pressure transducer, and temperature sensor, shock sensor etc.The sensor being arranged on equipment can be one, also can be for a plurality of.
S200, judges that arbitrary similarity between storage device status in described equipment state and state space is whether in preset range.
It should be noted that herein, need to build in advance according to monitored equipment the state space of the equipment state of the normal operation of storage plurality of devices.Generally, the detection information category of the sensor that the kind of the detection information of the sensor comprising in the storage device status comprising in state space receives while detecting with unit exception is identical, and the detection parameter number comprising is consistent.
S300, if so, determining apparatus is normally moved.
State space is set, and sets the standard of similarity.In the equipment state that step S100 is obtained and state space each storage device status compare, as long as current equipment state with any one the similarity of storage device status in preset range, think that current device is normally to move.It is carried out principle and can understand like this, if the state of the current running status of equipment and a known normal operation is enough approaching, this state also can be considered to normal operating condition so.Because when unit exception is moved, tend to cause equipment certain or some parameter to undergo mutation.
S400, if not, sends the false alarming information that equipment may be abnormal.
If the current equipment state detecting has larger difference with all states in the state space that prestores, (similarity is low, not within the scope of default similarity), so think that this state may, for unit exception running status, send warning message.
It should be noted that, described false alarming information refers to currently can not affirm that equipment is necessarily in abnormality herein, and whether it is finally defined as abnormality is determined by equipment debugging personnel or monitoring of equipment personnel.
As a kind of special case, state space can be also sky when starting abnormality detection, and the first equipment state now detecting can directly send without comparison other the false alarming information that equipment may be abnormal.
The method of unit exception state-detection in the Internet of Things of the embodiment of the present invention, a plurality of detection information structure equipment states of package, and equipment state and the state of the normal operation of the equipment prestoring are compared.If running status and default running status difference are very large, sending may be the false alarming information of misoperation, reminds related personnel to confirm to process.If equipment running status is little with respect to the running status difference of having stored in state space, think equipment normal operation.To the comprehensive a plurality of factors of the judgement of equipment running status, do not rely on merely the value of reading of sensor, accuracy of judgement, and pre-stored a plurality of normal operating condition, the running status that equipment is current and each normal operating condition compare, and can effectively reduce rate of false alarm.
In an embodiment, as shown in Figure 2, after the false alarming information that the equipment that sends may be abnormal, further comprising the steps of therein:
S500, waits for the confirmation of user to described false alarming information.
S600, when receiving the described false alarming information of the confirmation corresponding device abnormal operating condition of user's input, sends unit exception and reports to the police.By user (equipment debugging personnel or monitoring of equipment personnel), according to false alarming information, equipment running status is confirmed.User can check the true running status of equipment on the spot, and the variation that also can rule of thumb judge some parameter is in the normal range of operation of equipment, thereby determines that whether the current running status of equipment is abnormal.When user determines current device abnormal running, input corresponding confirmation, confirmation equipment is abnormal operating condition.In practical operation, the display interface of the computing machine that can move in this method shows the selection button of normal operation or misoperation.User can select according to judged result, thus input validation information.
S700, when receiving the described false alarming information of the confirmation corresponding device normal operating condition of user's input, stores described equipment state in described state space into.When user judges that current device normally moves, as previously mentioned, can select the button of unit exception operation, thus the abnormal input message of Returning equipment.Receive after the confirmation of the normal operation of equipment that user provides, current equipment state need to be stored in state space, so as in upper once unit exception state-detection using it as normal operating condition as a reference.
It should be noted that herein, the current running status of equipment is stored into after state space, current equipment state just becomes in state space a new storage device status for next abnormality detection.
The method of unit exception state-detection in the Internet of Things of the embodiment of the present invention, can progressively the optimizing with the increase that detects number of times of normal operating condition in state space, with the real running status of the equipment of following, this is significant in actual use.
Preferably, described described equipment state is stored in described state space after, as shown in Figure 3, can also comprise the following steps:
S800, judges whether the quantity of the described equipment state of storing in described state space is greater than preset value.
Along with equipment operation, may constantly there is new equipment normal operating condition to occur, so, if each normal operating condition is stored in state space, in the time of can causing subsequent calculations similarity, computing cost increases, and affects algorithm performance.Therefore, need to limit the sum of the equipment state that can store in state space.As maximal value is set is 8,10 or 12 etc., concrete numerical value can require to set according to the equipment running precision in the performance of the program executive agent of the inventive method and the Internet of Things detecting.
S900, if so, adopts the method for incremental clustering to optimize described state space.
S1000, if not, finishes this unit exception state-detection.
The method of unit exception state-detection in the Internet of Things of the embodiment of the present invention, meeting under the prerequisite of unit exception testing requirement, limits the number of the equipment state in state space, reduces calculated amount, accelerates detection speed.Meanwhile, adopt the mode of incremental clustering to be optimized state space, make the storage device status in state space more representative, unit exception detects more accurate, make to make a false report the frequency that alarming information occurs lower, gradually reduce manual operation, more intelligent.
As a kind of embodiment, in step S100, described detection information is analyzed, obtain the equipment state of described equipment, comprise the following steps:
S110, intercepts described detection information with the time window of predetermined width.
S120, the slope of the described detection information in the predetermined width that matching intercepts.Wherein, the number of slope equates with the test item number that described detection information comprises.
After obtaining the slope of the information that detects, all slopes are formed to a vector as aforesaid equipment state.Certainly storage device status is also pre-stored default vector.
Vector for equipment state, is described below:
By the state S in some moment of production equipment
dtbe expressed as the set of the related sensor value of reading:
S
Dt＝{v
1,v
2,...,v
n} v∈D (1)
Wherein, v representative is under the jurisdiction of the value of reading of the sensor of equipment D, and sensor and production equipment incidence relation are definite can be according to following three cardinal rules:
1) monitor the sensor of same equipment, belong in the set of this device sensor;
2) number of sensors increases and will cause the overexpansion of equipment state transition Spatial Dimension, needs further refinement (in the embodiment of the present invention, transformation is set as 8).For example can carefully draw according to sensor relative position subentry, outlet, directly under three classes;
3) allow only to have the situation of a sensor sign equipment state to occur.
To being under the jurisdiction of the value of the reading stream of same device sensor, as shown in Figure 4, the window that is T according to time dimension slip fixed width, and the slope of the value of reading in the window of matching simultaneously.Can adopt the least square method calculating sensor value of reading slope, its expression formula is:
According to the result of the Fitting Calculation, in time window T, the equipment state of equipment D is expressed as vector:
S
DT＝{k
1,k
2,...,k
n} (3)
Wherein, k
irepresentative sensor s
islope in the window that is T at width.Obviously, k
ivalue is larger, and status change more likely occurs equipment.It should be noted that between k, to have relative independentability, the namely variation of different sensors not necessarily meets same trend.For example, under isobaric environment, pressure is constant, and temperature can change; For equipment such as heating towers, the temperature variation of entrance can export significantly.
When carrying out unit exception state-detection, by S
dTcompare with the equipment state of having stored in state space, judge whether current device is abnormality.
It should be noted that, selection window T is 10S herein, the equipment running status that aforesaid current device running status is corresponding time window.The large I of window is selected according to the actual requirements.
In conjunction with the vector of aforesaid equipment state, step S200, judges that arbitrary similarity between storage device status in described equipment state and state space whether in preset range, comprises the following steps:
S210, the cosine angle between the vector of computing equipment state and all described default vector;
S220, whether the minimum described cosine angle of judgement is less than default angle, if so, described similarity in preset range; If not, described similarity not in preset range.
In conjunction with aforesaid fit slope, the vectorial S of the equipment state of the embodiment of the present invention
dTbe essentially equipment state transition vector, state space is status change space, adopts the state-detection algorithm (Status Space based Detection, SSD) based on status change space to detect the abnormal operating condition of equipment.
For detecting production equipment whether in normal operating conditions, core is to judge that whether current status change is reasonable, in other words, from a rational state, transit to another rational state, normal production behavior, otherwise, if there is a new equipment state, before user's acknowledgement state correctness, what should look is abnormality.
Conventionally, when production equipment is stablized, in status change window (window that aforesaid width is T), the value of reading slope is tending towards 0, and sensor value of reading now can not effectively be distinguished the residing state of production equipment.Therefore, should pay close attention to the effective transition process of production equipment state, identify the variation of its state.Take equipment D equally as example, and its effective status transition space may be defined as:
Ω
D＝{S
DT1,S
DT2,...,S
DTm} SIM(S
DTi,S
DTj)＞λ (4)
Status change space Ω wherein
dbuilding process as shown in Fig. 5 a to Fig. 5 d:
Assumed initial state, not yet there is status change in equipment, now
as shown in Figure 5 a.
Along with equipment running status changes, constantly there is new status change vector, as S
1, S
2join in situation transition space, its adition process as shown in Figure 5 b.
For the status change vector S newly collecting, calculate itself and the similarity of directed quantity, we adopt cosine angle to represent similarity degree, as shown in Figure 5 c.
If min is (Θ
1, Θ
2) > Θ
λ, depending on S, be new variation tendency, integrated with status change space, i.e. aforesaid state space, in, as shown in Fig. 5 d.
Concrete, step S900, adopts the method for incremental clustering to optimize described state space, comprises the following steps:
S910, increases the preset range of described similarity to the first preset range.As a kind of embodiment, the mode that can double increases similarity scope.
S920 merges into a new equipment state by similarity in the equipment state of having stored described in two of described the first preset range, and stores in described state space.After similarity scope increases, stored the similarity that there will be in a plurality of equipment states in state space between two adjacent equipment states in the first new preset range, now two contiguous equipment states are synthesized to an equipment state, can adopt the mode that the parameter of two equipment states is averaged to obtain a new equipment state with the mode becoming.
And, the first described preset range in the circulation of next unit exception state-detection as new preset range.
It should be noted that, as a kind of embodiment, if increase after the preset range of similarity, there is no the equipment state that can merge herein, can repeated execution of steps S910 and step S920.
For aforesaid state space Ω
d, specifically can adopt following steps to carry out the optimization of state space:
1) in status change space, number of vectors q+1 surpasses restriction P, execution step 2;
2) get Θ ' λ=2* Θ λ; I=1;
3) calculate respectively the angle of every a pair of adjacent vector, and ascending sequence Θ 1, and Θ 2 ..., Θ q};
4) if Θ i< Θ ' is λ, merge the vector (numerical value to these two each dimensions of vector averages, and generates a new vector) of Θ i both sides, make Θ λ=Θ ' λ, i=i+1;
5) if i<q, and the vectorial number q+1>P in state space, repeating step 3 is to step 5;
6) polymerization process finishes.
If polymerization process finishes, in state space, the number of vector still surpasses restriction P, sends serious warning, asks commissioning staff or monitoring of tools personnel to reaffirm whether the equipment state newly adding is equipment normal condition.If be really equipment normal operating condition, can consider to adjust the size of the number restriction P in state space, increase and manually increase new storage device status.
The choosing as the preset value of equipment state quantity in experiment sample description time window and state space below in conjunction with the actual production Monitoring Data of Yi Gemou factory.
Choose 3 typical production data, sample frequency is per minute 12 times, the situation of change in sampling time 2013.3.1 to 2013.4.30, and to 1,054,080 data is carried out statistical study.As shown in table 1: equipment D1 is characterized by two sensors, value fluctuates near maintaining average, and the less status change that embodies, therefore stability is strong; Equipment D2 is also by two Sensor monitorings, but the religion of some variation ranges is large, and occurs repeatedly saltus step, a little less than qualitative its stability; Equipment D3 is by three sensor sheet symptom states, stability disunity.
Table 1 test data sample
In SSD algorithm, the data of the time window matching equipment associated sensor of use sliding, window size and equipment state transition detect strong correlation.In test, getting window size is 60S, 120S, 240S and 600S, gets Θ
λ=3 degree angles, statistics detects number of times respectively.Result as shown in Figure 6.
When window T=60S, fall into Θ
λeffective status less, equipment 1 only detects 12 times, equipment 2 detects 60 times, equipment 3 detects 54 times; With window, increase, when T=120S, amount to 24 records and covered by window, now, reach the maximum effect that detects, equipment 2 has reached 90 next states and has detected; With window, increase, when T=600S, detect effect variation gradually, this is because excessive window makes to change slope real-time variation.Meanwhile, the number of times that detects in this experiment is consistent with the observation rule of raw data set, and D1 is the most stable, therefore detect least number of times.Visible, for this sample, it is the most suitable that the status change window of employing 120S detects state.
Relation between aggregation number generation and status change space size preset value P is discussed below.Getting P is 6,8,10 and 12, calculate respectively when window be 120S, initial value Θ
λthe number of times that during=1 degree angle, in SSD algorithm, polymerization occurs, obtains result as shown in Figure 7.Along with the increase gradually of preset value P, aggregation number all presents the trend of minimizing.But, when P value is 8 and 10, for equipment 2, all there is 5 polymerizations, that is to say, aggregation number is very inresponsive with respect to space size, considers the high efficiency of calculating, and desirable normal state space size is 8 or 10.
Based on same inventive concept, the present invention also provides the system of unit exception state-detection in a kind of Internet of Things, because the principle that this system is dealt with problems is similar to the systems approach of unit exception state-detection in aforesaid a kind of Internet of Things, therefore, the enforcement of this system can realize according to the concrete steps of preceding method, repeats part and repeats no more.
The system of unit exception state-detection in the Internet of Things of one embodiment of the invention, as shown in Figure 8, comprises information receiving and analyzing module 100, the first judge module 200, the first execution module 300 and the second execution module 400.Wherein: information receiving and analyzing module 100, for the detection information of receiving equipment running status, and described detection information is analyzed, obtain the equipment state of described equipment; The first judge module 200, for arbitrary similarity between storage device status of judging described equipment state that described information receiving and analyzing module generates and state space whether in preset range; The first execution module 300, for according to the judged result of described the first judge module, when described similarity is in described preset range, determining apparatus is normally moved, and waits the unit exception of pending next circulation to detect; The second execution module 400, for according to the judged result of described the first judge module, when described similarity is not in described preset range, sends the false alarming information that equipment may be abnormal.
The system of unit exception state-detection in the Internet of Things of the embodiment of the present invention, a plurality of detection information structure equipment states of package, and equipment state and the state of the normal operation of the equipment prestoring are compared.If running status and default running status difference are very large, sending may be the false alarming information of misoperation, reminds related personnel to confirm to process.If equipment running status is little with respect to the running status difference of having stored in state space, think equipment normal operation.To the comprehensive a plurality of factors of the judgement of equipment running status, do not rely on merely the value of reading of sensor, accuracy of judgement, and pre-stored a plurality of normal operating condition, the running status that equipment is current and each normal operating condition compare, and can effectively reduce rate of false alarm.
In an Internet of Things in the embodiment of the system of unit exception state-detection, as shown in Figure 9, also comprise alarm module 500 and storage execution module 600 therein.Wherein: alarm module 500, for when receiving the described false alarming information of the confirmation corresponding device abnormal operating condition of user's input, sends unit exception and reports to the police; Storage execution module 600, for when receiving the described false alarming information of the confirmation corresponding device normal operating condition of user's input, stores described equipment state in described state space into.
The system of unit exception state-detection in the Internet of Things of the embodiment of the present invention, can progressively the optimizing with the increase that detects number of times of normal operating condition in state space, with the real running status of the equipment of following, this is significant in actual use.
In an Internet of Things in the embodiment of the system of unit exception state-detection, as shown in figure 10, also comprise the second judge module 700, the 3rd execution module 800 and the 4th execution module 900 therein.Wherein: the second judge module 700, for judging whether the quantity of the described equipment state that described state space is stored is greater than preset value; The 3rd execution module 800, for according to the judged result of described the second judge module, when being greater than preset value, adopts the method for incremental clustering to optimize described state space; The 4th execution module 900, for according to the judged result of described the second judge module, when being less than or equal to preset value, finishes this unit exception state-detection.
The system of unit exception state-detection in the Internet of Things of the embodiment of the present invention, meeting under the prerequisite of unit exception testing requirement, limits the number of the equipment state in state space, reduces calculated amount, accelerates detection speed.Meanwhile, adopt the mode of incremental clustering to be optimized state space, make the storage device status in state space more representative, unit exception detects more accurate, make to make a false report the frequency that alarming information occurs lower, gradually reduce manual operation, more intelligent.
In an Internet of Things in the embodiment of the system of unit exception state-detection, also comprise the sensor of connection device therein, described information receiving and analyzing module receives the detection information of the described equipment running status of described sensor feedback.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (11)
1. a method for unit exception state-detection in Internet of Things, is characterized in that, comprises the following steps:
The detection information of receiving equipment running status, and described detection information is analyzed, the equipment state of described equipment obtained;
Judge that arbitrary similarity between storage device status in described equipment state and state space is whether in preset range;
If so, determining apparatus is normally moved;
If not, send the false alarming information that equipment may be abnormal.
2. the method for unit exception state-detection in Internet of Things according to claim 1, is characterized in that, step is if not, after the false alarming information that the equipment that sends may be abnormal, further comprising the steps of:
Wait for the confirmation of user to described false alarming information;
When receiving the described false alarming information of the confirmation corresponding device abnormal operating condition of user's input, send unit exception and report to the police;
When receiving the described false alarming information of the confirmation corresponding device normal operating condition of user's input, described equipment state is stored in described state space.
3. the method for unit exception state-detection in Internet of Things according to claim 2, is characterized in that, described described equipment state is stored in described state space after, further comprising the steps of:
Whether the quantity that judges the described equipment state of storing in described state space is greater than preset value;
If so, adopt the method for incremental clustering to optimize described state space;
If not, finish this unit exception state-detection.
4. the method for unit exception state-detection in Internet of Things according to claim 1, is characterized in that, the detection information exchange of described equipment running status is crossed the sensor being connected with described equipment and obtained.
5. the method for unit exception state-detection in Internet of Things according to claim 1, is characterized in that, described described detection information is analyzed, and obtains the equipment state of described equipment, comprises the following steps:
Time window with predetermined width intercepts described detection information;
The slope of the described detection information in the predetermined width that matching intercepts;
The number of described slope equates with the test item number that described detection information comprises;
The described equipment state vector that described slope forms of serving as reasons;
Described storage device status is pre-stored default vector.
6. the method for unit exception state-detection in Internet of Things according to claim 5, is characterized in that, judges that arbitrary similarity between storage device status in described equipment state and state space whether in preset range, comprises the following steps:
Cosine angle between the vector of computing equipment state and all described default vector;
Whether the minimum described cosine angle of judgement is less than default angle;
If so, described similarity in preset range;
If not, described similarity not in preset range.
7. the method for unit exception state-detection in Internet of Things according to claim 3, is characterized in that, the method for described employing incremental clustering is optimized described state space, comprises the following steps:
Increase the preset range of described similarity to the first preset range;
Similarity is merged into a new equipment state in the equipment state of having stored described in two of described the first preset range, and store in described state space;
Described the first preset range in the circulation of next unit exception state-detection as new preset range.
8. a system for unit exception state-detection in Internet of Things, is characterized in that, comprises information receiving and analyzing module, the first judge module, the first execution module and the second execution module, wherein:
Described information receiving and analyzing module, for the detection information of receiving equipment running status, and analyzes described detection information, obtains the equipment state of described equipment;
Described the first judge module, for arbitrary similarity between storage device status of judging described equipment state that described information receiving and analyzing module generates and state space whether in preset range;
Described the first execution module, for according to the judged result of described the first judge module, when described similarity is in described preset range, determining apparatus is normally moved, and waits the unit exception of pending next circulation to detect;
Described the second execution module, for according to the judged result of described the first judge module, when described similarity is not in described preset range, sends the false alarming information that equipment may be abnormal.
9. the system of unit exception state-detection in Internet of Things according to claim 8, is characterized in that, also comprises alarm module and storage execution module, wherein:
Described alarm module, for when receiving the described false alarming information of the confirmation corresponding device abnormal operating condition of user's input, sends unit exception and reports to the police;
Described storage execution module, for when receiving the described false alarming information of the confirmation corresponding device normal operating condition of user's input, stores described equipment state in described state space into.
10. the system of unit exception state-detection in Internet of Things according to claim 9, is characterized in that, also comprises the second judge module, the 3rd execution module and the 4th execution module, wherein:
Described the second judge module, for judging whether the quantity of the described equipment state that described state space is stored is greater than preset value;
Described the 3rd execution module, for according to the judged result of described the second judge module, when being greater than preset value, adopts the method for incremental clustering to optimize described state space;
Described the 4th execution module, for according to the judged result of described the second judge module, when being less than or equal to preset value, finishes this unit exception state-detection.
In 11. Internet of Things according to claim 8, the system of unit exception state-detection, is characterized in that, also comprises the sensor of connection device, and described information receiving and analyzing module receives the detection information of the described equipment running status of described sensor feedback.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410305059.1A CN104075749A (en) | 2014-06-30 | 2014-06-30 | Abnormal state detecting method and system for equipment in internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410305059.1A CN104075749A (en) | 2014-06-30 | 2014-06-30 | Abnormal state detecting method and system for equipment in internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104075749A true CN104075749A (en) | 2014-10-01 |
Family
ID=51597181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410305059.1A Pending CN104075749A (en) | 2014-06-30 | 2014-06-30 | Abnormal state detecting method and system for equipment in internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104075749A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104601401A (en) * | 2014-12-26 | 2015-05-06 | 珠海格力电器股份有限公司 | Detection method, device and system of cloud control household appliances |
| CN104750144A (en) * | 2015-02-03 | 2015-07-01 | 北京金控自动化技术有限公司 | Method of early warning operating condition of equipment |
| CN104848885A (en) * | 2015-06-04 | 2015-08-19 | 北京金控自动化技术有限公司 | Method for predicting time of future failure of equipment |
| CN106292604A (en) * | 2016-09-09 | 2017-01-04 | 深圳市智物联网络有限公司 | A kind of control terminal being applied to industry Internet of Things |
| WO2017124446A1 (en) * | 2016-01-23 | 2017-07-27 | 张阳 | Method and system for managing devices in theatre |
| CN107770796A (en) * | 2016-08-17 | 2018-03-06 | 西门子公司 | Node state detection method and equipment for non-network type alignment system |
| CN107947972A (en) * | 2017-11-16 | 2018-04-20 | 长安大学 | A kind of sensing node abnormal operating condition detection method and detection device |
| CN108011943A (en) * | 2017-11-29 | 2018-05-08 | 陈裕通 | A kind of airport bird scaring linked system based on Internet of Things |
| CN109643492A (en) * | 2016-09-29 | 2019-04-16 | 松下知识产权经营株式会社 | Transducer fault detection device and its control method |
| CN110095144A (en) * | 2018-01-30 | 2019-08-06 | 中电长城(长沙)信息技术有限公司 | A kind of terminal device local fault recognition method and system |
| CN110286656A (en) * | 2019-05-07 | 2019-09-27 | 清华大学 | A kind of the false-alarm filter method and device of wrong data tolerance |
| CN111404777A (en) * | 2020-03-12 | 2020-07-10 | 黄成驰 | Internet of things equipment performance detection method, device and system |
| CN111565119A (en) * | 2020-04-24 | 2020-08-21 | 李振福 | Internet of things management method and system |
| CN111935180A (en) * | 2020-09-24 | 2020-11-13 | 杭州海康威视数字技术股份有限公司 | Active defense method, device and system for security equipment |
| WO2021036465A1 (en) * | 2019-08-30 | 2021-03-04 | 北京国双科技有限公司 | Edge device processing method and apparatus, storage medium, and processor |
| CN112565015A (en) * | 2020-12-03 | 2021-03-26 | 深圳华制智能制造技术有限公司 | Internet of things communication method and device, computer equipment and storage medium |
| WO2021120010A1 (en) * | 2019-12-17 | 2021-06-24 | Orange | Methods and apparatus to identify abnormal behavior within sets of internet-of-things devices |
| CN116008634A (en) * | 2023-03-22 | 2023-04-25 | 南京中旭电子科技有限公司 | Data processing method and device suitable for Hall current sensor |
| CN117251749A (en) * | 2023-11-17 | 2023-12-19 | 陕西通信规划设计研究院有限公司 | Data processing method of Internet of things based on incremental analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000346681A (en) * | 1999-06-02 | 2000-12-15 | Japan Nuclear Cycle Development Inst States Of Projects | Abnormality diagnostic device |
| JP2008059270A (en) * | 2006-08-31 | 2008-03-13 | Toshiba Corp | Process abnormality diagnostic device and process monitoring system |
| CN101487865A (en) * | 2008-01-16 | 2009-07-22 | 西门子公司 | Fault diagnosis method and fault diagnosis system |
| CN102243497A (en) * | 2011-07-25 | 2011-11-16 | 江苏吉美思物联网产业股份有限公司 | Networking technology-based remote intelligent analysis service system used for engineering machinery |
| CN102354206A (en) * | 2011-07-25 | 2012-02-15 | 山东建筑大学 | System and method for diagnosing air conditioner failure based on data fusion in internet-of-things environment |
| CN102880115A (en) * | 2012-09-29 | 2013-01-16 | 佛山喜讯电子科技有限公司 | Remote collaborative diagnosis system of numerical-control machine tool on basis of internet of things |
-
2014
- 2014-06-30 CN CN201410305059.1A patent/CN104075749A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000346681A (en) * | 1999-06-02 | 2000-12-15 | Japan Nuclear Cycle Development Inst States Of Projects | Abnormality diagnostic device |
| JP2008059270A (en) * | 2006-08-31 | 2008-03-13 | Toshiba Corp | Process abnormality diagnostic device and process monitoring system |
| CN101487865A (en) * | 2008-01-16 | 2009-07-22 | 西门子公司 | Fault diagnosis method and fault diagnosis system |
| CN102243497A (en) * | 2011-07-25 | 2011-11-16 | 江苏吉美思物联网产业股份有限公司 | Networking technology-based remote intelligent analysis service system used for engineering machinery |
| CN102354206A (en) * | 2011-07-25 | 2012-02-15 | 山东建筑大学 | System and method for diagnosing air conditioner failure based on data fusion in internet-of-things environment |
| CN102880115A (en) * | 2012-09-29 | 2013-01-16 | 佛山喜讯电子科技有限公司 | Remote collaborative diagnosis system of numerical-control machine tool on basis of internet of things |
Non-Patent Citations (2)
| Title |
|---|
| 吕晓鹏: "工业物联网中的设备状态建模与检测", 《科技创新与应用》, no. 31, 10 November 2013 (2013-11-10) * |
| 王天真等: "基于动态数据窗口的融合聚类分析与故障检测", 《华中科技大学学报(自然科学版)》, vol. 37, no. 1, 30 August 2009 (2009-08-30) * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104601401B (en) * | 2014-12-26 | 2018-04-13 | 珠海格力电器股份有限公司 | High in the clouds controls detection method, the device and system of household electrical appliance |
| CN104601401A (en) * | 2014-12-26 | 2015-05-06 | 珠海格力电器股份有限公司 | Detection method, device and system of cloud control household appliances |
| CN104750144B (en) * | 2015-02-03 | 2017-01-11 | 北京金控数据技术股份有限公司 | Method of early warning operating condition of equipment |
| CN104750144A (en) * | 2015-02-03 | 2015-07-01 | 北京金控自动化技术有限公司 | Method of early warning operating condition of equipment |
| CN104848885B (en) * | 2015-06-04 | 2017-05-10 | 北京金控数据技术股份有限公司 | Method for predicting time of future failure of equipment |
| CN104848885A (en) * | 2015-06-04 | 2015-08-19 | 北京金控自动化技术有限公司 | Method for predicting time of future failure of equipment |
| WO2017124446A1 (en) * | 2016-01-23 | 2017-07-27 | 张阳 | Method and system for managing devices in theatre |
| CN107770796A (en) * | 2016-08-17 | 2018-03-06 | 西门子公司 | Node state detection method and equipment for non-network type alignment system |
| CN107770796B (en) * | 2016-08-17 | 2021-07-09 | 西门子公司 | Node state detection method and equipment for non-network type positioning system |
| CN106292604A (en) * | 2016-09-09 | 2017-01-04 | 深圳市智物联网络有限公司 | A kind of control terminal being applied to industry Internet of Things |
| CN109643492A (en) * | 2016-09-29 | 2019-04-16 | 松下知识产权经营株式会社 | Transducer fault detection device and its control method |
| CN107947972A (en) * | 2017-11-16 | 2018-04-20 | 长安大学 | A kind of sensing node abnormal operating condition detection method and detection device |
| CN107947972B (en) * | 2017-11-16 | 2021-01-15 | 长安大学 | Detection method and detection device for sensing abnormal operation state of node |
| CN108011943A (en) * | 2017-11-29 | 2018-05-08 | 陈裕通 | A kind of airport bird scaring linked system based on Internet of Things |
| CN110095144A (en) * | 2018-01-30 | 2019-08-06 | 中电长城(长沙)信息技术有限公司 | A kind of terminal device local fault recognition method and system |
| CN110095144B (en) * | 2018-01-30 | 2021-07-09 | 中电长城(长沙)信息技术有限公司 | Method and system for identifying local fault of terminal equipment |
| CN110286656A (en) * | 2019-05-07 | 2019-09-27 | 清华大学 | A kind of the false-alarm filter method and device of wrong data tolerance |
| CN110286656B (en) * | 2019-05-07 | 2020-07-17 | 清华大学 | False alarm filtering method and device for tolerance of error data |
| WO2021036465A1 (en) * | 2019-08-30 | 2021-03-04 | 北京国双科技有限公司 | Edge device processing method and apparatus, storage medium, and processor |
| WO2021120010A1 (en) * | 2019-12-17 | 2021-06-24 | Orange | Methods and apparatus to identify abnormal behavior within sets of internet-of-things devices |
| CN111404777A (en) * | 2020-03-12 | 2020-07-10 | 黄成驰 | Internet of things equipment performance detection method, device and system |
| CN111565119A (en) * | 2020-04-24 | 2020-08-21 | 李振福 | Internet of things management method and system |
| CN111935180A (en) * | 2020-09-24 | 2020-11-13 | 杭州海康威视数字技术股份有限公司 | Active defense method, device and system for security equipment |
| CN112565015A (en) * | 2020-12-03 | 2021-03-26 | 深圳华制智能制造技术有限公司 | Internet of things communication method and device, computer equipment and storage medium |
| CN112565015B (en) * | 2020-12-03 | 2021-08-17 | 深圳华制智能制造技术有限公司 | Internet of things communication method and device, computer equipment and storage medium |
| CN116008634A (en) * | 2023-03-22 | 2023-04-25 | 南京中旭电子科技有限公司 | Data processing method and device suitable for Hall current sensor |
| CN116008634B (en) * | 2023-03-22 | 2023-06-09 | 南京中旭电子科技有限公司 | Data processing method and device suitable for Hall current sensor |
| CN117251749A (en) * | 2023-11-17 | 2023-12-19 | 陕西通信规划设计研究院有限公司 | Data processing method of Internet of things based on incremental analysis |
| CN117251749B (en) * | 2023-11-17 | 2024-02-27 | 陕西通信规划设计研究院有限公司 | Data processing method of Internet of things based on incremental analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104075749A (en) | Abnormal state detecting method and system for equipment in internet of things | |
| KR101774233B1 (en) | System for Detecting Sensor Signal and smart plug comprising the same | |
| EP3361343B1 (en) | Event analyzing device, event analyzing system, event analyzing method, and non-transitory computer readable storage medium | |
| US7966152B2 (en) | System, method and algorithm for data-driven equipment performance monitoring | |
| US9207670B2 (en) | Degrading sensor detection implemented within a transmitter | |
| CN104020724B (en) | alarm monitoring method and device | |
| CN109641602A (en) | Abnormality detecting apparatus, method for detecting abnormality and non-transitory computer-readable medium | |
| US9568204B2 (en) | Systems and methods for rapid disturbance detection and response | |
| CN105242534B (en) | Based on telemetry parameter and it is associated with the satellitosis monitoring method to satellite controlling behavior | |
| KR100839071B1 (en) | A system and method for monitoring conditions of a processing tool | |
| US20170059373A1 (en) | Hvac system with automated flow direction detection | |
| JP2019079356A (en) | Abnormality detection system and abnormality detection method | |
| CN109577892B (en) | Intelligent overflow detection system and early warning method based on downhole parameters | |
| WO2009129042A1 (en) | Automated system for checking proposed human adjustments to operational or planning parameters at a plant | |
| CN104566820A (en) | Air conditioner, air conditioner control method and air conditioner control device | |
| CN103389427B (en) | GIS equipment operational condition online test method and system | |
| CN117032004A (en) | Industrial production automatic control platform based on Internet of things | |
| CN110878983B (en) | Air conditioner fault determination method and device | |
| CN105629959A (en) | Industrial process fault detection method | |
| CN105425739A (en) | System for predicting abnormality occurrence using PLC log data | |
| CN102330608B (en) | Systems and methods for determining steady state conditions in a gas turbine | |
| WO2022242224A1 (en) | Indoor temperature measuring method and apparatus, and intelligent air conditioner | |
| CN113465120B (en) | Method and device for detecting indoor temperature and intelligent air conditioner | |
| KR102162427B1 (en) | Method for monitering abnormality judgment of machine tool | |
| JP2019003238A (en) | Abnormality detection device and abnormality detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20141001 |
|
| WD01 | Invention patent application deemed withdrawn after publication |