CN114664058A - Integral fault early warning system and method for fire water system - Google Patents
Integral fault early warning system and method for fire water system Download PDFInfo
- Publication number
- CN114664058A CN114664058A CN202210113091.4A CN202210113091A CN114664058A CN 114664058 A CN114664058 A CN 114664058A CN 202210113091 A CN202210113091 A CN 202210113091A CN 114664058 A CN114664058 A CN 114664058A
- Authority
- CN
- China
- Prior art keywords
- fire
- data
- water system
- early warning
- detection
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 100
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000001514 detection method Methods 0.000 claims description 74
- 239000013598 vector Substances 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 239000007788 liquid Substances 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 239000006260 foam Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000006467 substitution reaction Methods 0.000 claims description 2
- 238000004078 waterproofing Methods 0.000 abstract description 8
- 230000036541 health Effects 0.000 abstract description 5
- 238000004422 calculation algorithm Methods 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000005507 spraying Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000005871 repellent Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- A—HUMAN NECESSITIES
- A62—LIFE-SAVING; FIRE-FIGHTING
- A62C—FIRE-FIGHTING
- A62C37/00—Control of fire-fighting equipment
- A62C37/50—Testing or indicating devices for determining the state of readiness of the equipment
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/04—Hydraulic or pneumatic actuation of the alarm, e.g. by change of fluid pressure
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Fluid Mechanics (AREA)
- Fire-Extinguishing By Fire Departments, And Fire-Extinguishing Equipment And Control Thereof (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides an overall fault early warning system and method for a fire-fighting water system, wherein real-time fault risk early warning of the overall fire-fighting water system in a building is realized by an MCUSUM Control Chart method, the relation between historical data and real-time data at a single point of the water system of the Internet of things is considered by the algorithm, and the fault problem which possibly occurs in the overall water system can be quickly and effectively found and early warning is given; according to the result feedback of the algorithm, the method can help building units to quickly evaluate the overall health condition of the fire-fighting and water-proofing system, send early warning to possible problems, lock the aspect of needing to be promoted in the fire-fighting water system, help social units to carry out self-check and self-change of the safety risk of the fire-fighting water system, help to reduce the fault occurrence rate of the fire-fighting water system of each building unit when fire is extinguished, help to improve the fire-fighting and self-rescue capacity of the social units, and help to improve the real-time supervision capacity of government supervision departments on the safety level of the fire-fighting water system of each building unit.
Description
Technical Field
The invention relates to the field of fire fighting equipment detection and early warning, in particular to an overall fault early warning system and method for a fire fighting water system.
Background
Along with the improvement of the safety consciousness of residents, the fire safety level is also paid more attention. In order to improve the fire safety level of a region, a fire-fighting water system and other fire-fighting facilities are usually arranged on site, so that fire-fighting personnel or masses can rapidly obtain fire-fighting equipment and resources, and the fire-fighting work is finished at the first time. Due to the special use of the fire-fighting equipment, the fire-fighting equipment is required to be kept in a usable state, so that the fire-fighting equipment is extremely important for fault detection and early warning of the fire-fighting equipment. Wherein to the fire control facility of equipment such as fire extinguisher, can effectively avoid trouble scheduling problem through periodic replacement equipment, but to fire water system, be difficult to change, still have a large amount of hidden dangers, including pressure leakage, excessive pressure, weeping, body rupture etc. on the other hand, according to the data display of conflagration investigation report, the operation health condition of fire water system equipment has played extremely crucial effect to the fire extinguishing effect, consequently need detect it.
In the existing method, the fire protection maintenance worker usually performs fault detection and health condition supervision on the fire protection and protection system regularly, including modes of manual sampling, statistics, analysis and inspection and the like, and the method has the following disadvantages: firstly, regular and sampling inspection of fire protection maintenance workers is difficult to ensure the real-time performance of a fire protection water system at each single point; secondly, the detection data is recorded and uploaded by personnel, the data volume is small, and systematic detection evaluation and early warning processes are lacked; thirdly, the efficiency of data collection is low by manual inspection, and the phenomenon of fraud is easy to occur.
In addition, in the existing fire fighting water system, although a large number of internet of things devices for detecting liquid level hydraulic values of all important nodes are installed in the water system, the data are usually only used for assisting maintenance personnel to judge whether the water system is normal, and information contained in real-time data and historical data of all the devices is not fully utilized. On the other hand, through the data of the fire investigation report, the operation health condition of the fire-fighting water system equipment is easily discovered to play a very critical role in the fire-fighting effect. Therefore, based on the data of the fire-fighting internet of things, the real-time and automatic fire-fighting water system fault detection and early warning are realized, the health level of the fire-fighting water system is improved for a building unit, the fire extinguishing capacity of the water system is enhanced, and the daily operation and maintenance of people in charge of safety are facilitated.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an integral fault early warning system and method for a fire fighting water system.
In order to solve the problems, the invention adopts the following technical scheme:
an integral fault early warning method for a fire water system comprises the following steps:
step 1: the detection sensor acquires analog quantity data acquired by the detection sensor and transmits the analog quantity data to the edge computing gateway in a one-way mode;
step 2: the edge computing gateway receives data collected by the detection sensor;
and step 3: the method comprises the steps that an edge computing gateway obtains data collected by all detection sensors in a fire fighting water system, and the collected data are analyzed according to a multivariable CUSUM Control Chart method, so that risk early warning of the whole fire fighting water system is completed;
and 4, step 4: sending the risk early warning result to receiving equipment in a communication mode, wherein the receiving equipment comprises a mobile phone, a computer and an Internet of things data center;
and 5: and the data center of the Internet of things receives and stores the data.
Further, in the step 3, the early warning of the whole fire fighting and water preventing system firstly needs to acquire the historical data X of the whole fire fighting and water preventing system in a normal stateIC={X1,X2,X3,…,XnEach data variable XiIs represented as Xi=[Xi1Xi2…Xim]TM represents the vector dimension of the data variable, in this case the number of sensors in the fire-fighting water system; calculating to obtain historical mean dataExpressed as:
next, a sample variance S is obtained, expressed as:
for sensor group data obtained over a new period of time, denoted as Y1,Y2,Y3,…,YtWherein each variable YiAre all m-dimensional vectors, Yi=[Yi1 Yi2…Yim]T(ii) a Acquiring the mean value of the sensor group data in the period of time, and finally expressing the obtained mean value of the data as mu; and proposes the hypothesis:
in the MCUMSUM method, two variables s are set in an iterative manneri and CiRespectively expressed as:
where the parameter k is set by the allowable deviation of each sensor and the mean dataObtaining a sample variance S;
by a variable si and CiObtaining a detection mean judgment bit ZiJudging the obtained detection mean value to be ZiAnd comparing the signal with a set value h to judge whether to give out early warning.
Further, the parameter k is obtained by the following formula:
wherein p is m-dimensional vector, and each value p in the vectori∈[-1,1],i=1,2,…,m;100·pi% represents the maximum mean deviation percentage allowed by the ith sensor.
Further, the detection mean judgment bit ZiThe acquisition method of (a) is represented as:
substitution into siObtaining:
Further, in said step 3, if Z isiIf the detection time is more than h, the state change of the fire fighting water system is considered to be large in the detection time, and early warning is given out; otherwise, the fire-fighting water system is considered to work stably.
The overall fault early warning system of the fire water system is based on the method, and comprises a detection sensor, an edge computing gateway and an Internet of things data center; wherein the detection sensor is arranged in the fire-fighting water system; the edge computing gateway is connected with the detection sensors and can receive real-time data detected by the detection sensors; the edge computing gateway is also connected with the data center of the Internet of things.
Furthermore, the fire water system comprises an automatic water spraying fire extinguishing system, a foam fire extinguishing system, a fire pool, a water tank and a pipeline, wherein the fire pool and the water tank are connected with the automatic water spraying fire extinguishing system and the foam fire extinguishing system through the pipeline.
Further, the detection sensor comprises a hydraulic sensor and a liquid level sensor, wherein the hydraulic sensor is arranged at the junction and corner parts of the pipeline; the liquid level sensor is arranged at the fire pool and the water tank.
Further, the edge gateway comprises a storage module, a processing module and a communication module; the processing module is used for processing the data collected by the detection sensor; the communication module is used for connecting the data center of the Internet of things and external equipment; the storage module is used for storing detection data acquired by the detection sensor.
The invention has the beneficial effects that:
the water pressure, water level and other data at a single point in the fire-fighting and water-proofing system are collected, the collected data are transmitted to the edge computing gateway, and the data are uploaded uniformly by the edge computing gateway to form a systematic automatic detection layout, so that the real-time supervision and reexamination level of the fire-fighting and water-proofing system is improved, and the normal operation of the fire-fighting and water-proofing system is effectively guaranteed;
the method comprises the steps of carrying out fault detection on a single point of a fire-fighting and water-proofing system through an X Control Chart method, carrying out early warning on the single point of the fire-fighting and water-proofing system based on a CUSUM Control Chart method, feeding back possible faults in a water system to an owner or a related part in time, carrying out early warning on potential problems in advance, improving the fire-fighting level and guaranteeing social safety;
predicting the overall operation condition of the fire-fighting water system by a Multivariate Shewhart Control Chart method in combination with data acquired by a detection sensor in the whole fire-fighting water system, and accurately detecting partial point position abnormity in the fire-fighting water system;
the set value h used for comparison in the early warning process is continuously iterated by combining the normal operation data continuously collected by a detection sensor in the fire fighting water system through a multivariable CUSUM Control Chart method, and the accuracy of the early warning result is ensured.
Drawings
FIG. 1 is a system connection diagram according to a first embodiment of the present invention;
FIG. 2 is a graph showing the variation of the latest data collected by four detecting sensors according to the first embodiment of the present invention;
FIG. 3 is a diagram of a mean determination bit Z according to a first embodiment of the present inventioniA curve of variation.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The first embodiment is as follows:
as shown in fig. 1, an overall fault early warning system of a fire fighting water system comprises a detection sensor, an edge computing gateway and an internet of things data center; wherein the detection sensor is arranged in the fire-fighting water system; the edge computing gateway is connected with the detection sensors and can receive real-time data detected by the detection sensors; the edge computing gateway is also connected with the data center of the Internet of things.
The fire-fighting water system comprises an automatic water spray fire-fighting system, a foam fire-fighting system, a fire pool, a water tank and a pipeline, wherein the fire pool and the water tank are connected with the automatic water spray fire-fighting system and the foam fire-fighting system through the pipeline, and the stored water in the fire pool and the water tank is transported to all parts in a building.
The detection sensor comprises a hydraulic sensor and a liquid level sensor, wherein the hydraulic sensor is arranged at the position of a junction, a corner and the like of the pipeline, and the pipeline position has important significance for the whole fire water system and is easy to have hidden danger; in this example, the installation position of the hydraulic pressure sensor also comprises a position of a floor end water testing device. The liquid level sensor is arranged at the fire pool and the water tank.
The edge gateway comprises a storage module, a processing module and a communication module; the processing module is used for processing the data collected by the detection sensor; the communication module is used for connecting the data center of the internet of things and external equipment, such as a mobile phone, a computer, a tablet computer and the like; the storage module is used for storing detection data acquired by the detection sensor.
An integral fault early warning method for a fire water system comprises the following steps:
step 1: the detection sensor acquires analog quantity data acquired by the detection sensor and transmits the analog quantity data to the edge computing gateway in a one-way mode;
step 2: the edge computing gateway receives data collected by the detection sensor, wherein the data comprises liquid level data and hydraulic data;
and step 3: the method comprises the steps that an edge computing gateway obtains data collected by all detection sensors in a fire fighting water system, and analyzes the collected data according to a set algorithm to finish risk early warning of the whole fire fighting water system;
and 4, step 4: sending the risk early warning result to a receiving device in a communication mode, wherein the receiving device comprises a mobile phone, a computer and an Internet of things data center; the communication mode comprises 4G/5G, wireless network and the like;
and 5: and the data center of the Internet of things receives and stores the data.
The method for performing fault early warning on the whole fire-fighting and water-proofing system in the step 3 is a multivariable CUSUM Control Chart (MCUSUM) method, and whether the average attribute of the whole fire-fighting and water-proofing system deviates or not is judged. In the judgment process, firstly, the historical data X of the whole fire fighting water system in a normal state needs to be acquiredIC={X1,X2,X3,…,XnEach data variable XiIs represented as Xi=[Xi1 Xi2…Xim]TM represents the vector dimension of the data variable, m in this case representing the number of sensors detected in the fire-fighting water system, and X represents each data variableiThe analog data obtained by all sensors at a certain time is equal. Calculating to obtain mean dataExpressed as:
for sensor group data obtained over a new period of time, denoted as Y1,Y2,Y3,…,YtWherein each variable YiAre all m-dimensional vectors, Yi=[Yi1 Yi2…Yim]T(ii) a And acquiring a mean value of the sensor group data in the period, wherein the acquired data of each detection sensor needs to be respectively averaged, and the finally obtained mean value of the data is expressed as mu. To determine whether there is a trend of change in the analog mean value, the following assumptions are made:
in the MCUMSUM method, two variables s are set in an iterative manneri and CiRespectively expressed as:
wherein the parameter k is obtained by:
wherein p is m-dimensional vector, and each value p in the vectori∈[-1,1],i=1,2,…,m;100.pi% represents the maximum mean deviation percentage allowed by the ith sensor.
By a variable si and CiObtaining a detection mean judgment bit Zi:
Substituting the formula into the detection mean judgment position ZiIn (1), obtaining:
judging the obtained detection mean value ZiIs compared with a set value h, wherein if ZiIf the detection time is more than h, the state change of the fire fighting water system is considered to be large in the detection time, and early warning is given out; otherwise, the fire-fighting water system is considered to work stably. It should be noted that the set value h is expressed as the upper control limit of the fire-fighting water system in the MCUSUM method; the parameter is influenced by Average Run Length (ARL), the ARL represents an Average value of a large number of groups of experimental samples, in this example, the number of samples increases with the continuous data acquisition of the sensor, that is, the set value h changes with the data acquired by the sensor according to a set algorithm, and in this example, the size of the set value h is related to the number m of the detection sensors, the sample data amount and the value of the parameter k obtained by calculation. When the sample data is updated iteratively, that is, the sample data is infinite under an ideal condition, the value of the set value h is as shown in the following table:
as shown in fig. 2, in the implementation processFirstly, acquiring the collected data of four detection sensors in the multivariable CUSUM Control Chart method according to the process in the step 3, as shown in FIG. 2; obtaining historical mean data from the collected data
A sample variance S is obtained, expressed as:
acquiring newly acquired data of the detection sensor, in this example, 25 groups of data; and obtaining a detection mean judgment bit ZiAnd plotted as shown in FIG. 3, wherein the left graph in FIG. 3 is Z for 25 sets of dataiThe right graph is a partial enlarged graph.
According to the formula, the value of the parameter k is close to 0.5, the number of the detection sensors is 4, so that the set value h obtained according to the table is between 6.9 and 9.4, and the larger value is 9.4. As shown in the enlarged partial view, only the data before the second detected data point does not exceed 9.4, including the 0 point on the abscissa, so that the Z of the subsequent 23 detected points is considerediThe value is inevitably greater than the set value h when the number of the detection sensors is 4 and the parameter k is 0.5, which indicates that the average state of the fire water system at the time corresponding to the subsequent 23 detection data points has deviation, and conforms to the situation shown in fig. 2, except that the average value of the first detection sensor does not have large change, the average values of the other three sensor data are all greatly lower than the historical average value, and at this time, an early warning should be sent.
Example two:
the embodiment is obtained by improvement based on the first embodiment, wherein before performing the overall fault early warning in step 3, the fault judgment of the single-point part of the water-repellent system is also completed according to the data collected by the detection sensor arranged at the single-point by the X Control Chart method, and the method specifically includes the following steps:
firstly, a historical data set X of a single-point part in a normal state needs to be acquiredIC,XIC={X1,X2,X3,…,Xn}; from historical data set XICObtaining mean dataExpressed as:
according to mean value dataAnd a historical data set XICObtaining a sample standard deviation sigma as:
obtaining an upper bound UCL from the sample standard deviationsAnd lower bound LCLsUpper bound UCLsAnd a lower bound LCLsExpressed as:
wherein the parameter tn-1,αRepresents the critical value of Student t distribution when the degree of freedom is n-1 and the Type I error (Type I error) is alpha; in this example a is set to 2.5%.
According to the obtained upper bound UCLsAnd lower bound LCLsTo the current data XAnd (3) analysis: if LCLs≤X≤UCLsIf the analog quantity data are normal, the working state of the fire water system at the point is inferred to be normal; if LCLsThe analog quantity data is considered to be lower than the historical data in the statistical sense, and the conditions of pressure leakage, undervoltage, leakage and the like of the fire water system at the point are inferred; if UCLsX, and if the data of the analog quantity is considered to be higher than the historical data in a statistical sense, the fire water system at the point is inferred to be in an overpressure condition.
After the single-point part fault detection of the fire fighting water system is completed, the risk early warning is completed on the single-point part by combining the CUSUM Control Chart method according to the historical data and the current data collected by the detection sensor. Wherein the process of risk early warning includes:
first, a history data set X of a normal state is obtainedIC={X1,X2,X3,…,XnAnd mean dataIn order to determine whether there is a trend of increasing the average value of the analog quantity data collected by the sensor, the following assumptions are made:
H1: mean value of μ1,(μ1>μ0);
For a new time period t, the analog data set X collected by all the detection sensorsT={XT1,XT2,XT3,…,XTtDefine the variables for the analog data collected at the current time within the latest time period t in this exampleTo measure the analog quantity data set XTData in (1) and mean value μ0The difference between them:
wherein ,Δ1=μ1-μ0(ii) a For detecting the analog data set X in the time period tTTo predict future increasing trend, calculating an upper bound of two UCLsCUsUMAnd a lower bound of two LCLsCUsUMExpressed as:
wherein alpha and beta are set values, alpha is a type I error, and beta is a type II error; two UCLs according to an upper boundCUSUMAnd a lower bound of two LCLsCUSUMJudging the simulation data set XTWhether there is an increasing trend in the mean of (a), wherein: if it isJudging that the average value does not become high, and not performing early warning; if it isJudging that the average value has an increasing trend, considering that the fire fighting water system has a risk of overpressure at the moment, and sending out an early warning; if it isAnd judging that more data is needed, judging that the current data quantity is not enough to draw a statistically significant conclusion, and not giving early warning.
Similarly, in order to determine whether there is a tendency for the average value of the analog quantity data collected by the sensor to decrease, the following assumption is made:
H2: mean value of μ2,(μ2<μ0);
For the new time period t analog data set XT={XT1,XT2,XT3,…,XTtDefine the variable for the analog data in the time period t collected at the current time in this exampleTo measure the analog data set XTData in (1) and mean value μ0The difference between them:
wherein ,Δ2=μ2-μ0(ii) a In order to detect the analog data set X in the time period tTTo predict future trends in the reduction, computing a upper bound of three UCLsCUsUMAnd a lower bound of three LCLsCUsUMExpressed as:
wherein alpha and beta are set values, alpha is a type I error, and beta is a type II error; three UCL according to upper boundCUSUMAnd a lower bound of three LCLsCUSUMJudging the simulation data set XTWhether there is a decreasing trend in the mean of (a), wherein: if it isIt was judged that the average value did not become highNo early warning is made; if it isJudging that the average value has a decreasing trend, considering that the risk of pressure leakage and underpressure possibly exists in the fire water system at the moment, and sending out an early warning; if it isAnd judging that more data are needed, judging that the current data quantity is not enough to make a statistically meaningful conclusion, and not giving early warning.
Example three:
the embodiment is obtained by improvement based on the first embodiment, wherein in the step 3, before the warning of the whole fault of the fire-fighting water system, the whole fire-fighting water system is detected and judged according to the whole data collected by the corresponding fire-fighting water system, wherein the judging method is a Multivariate Shewhart Control Chart method. The judging process comprises the following steps: firstly, historical data X of the whole fire fighting water system in a normal state needs to be acquiredIc={X1,X2,X3,…,Xn}, each data variable XiIs represented as Xi=[Xi1Xi2…Xim]TM represents the vector dimension of the data variable, in this case the number of sensors in the fire-fighting water system; calculating to obtain mean dataExpressed as:
the sample variance S is expressed as:
for newly acquired data X, the distance T between the vector and the distribution formed by the IC data is described by the Mahalanobis distance, where the distance T has the following relationship:
wherein T2Approximately obeys F distribution, and therefore T can be obtained2Upper control limit UCL of (1)MSCCComprises the following steps:
wherein ,Fα(m, n-m) represents the critical value (critical value) of the F distribution when the Type I error (Type I error) is alpha and the degrees of freedom are m, n-m respectively; in this example, α is 2.5%.
Judgment of T2And an upper control limit UCLMSCCIf T is2>UCLMSCCIf the fire water system is in the normal working state, judging that the whole working state of the fire water system at the moment corresponding to the newly acquired data X is abnormal; otherwise, the working state is considered to be normal.
The above description is only a specific example of the present invention and should not be construed as limiting the invention in any way. It will be apparent to persons skilled in the relevant art(s) that, having the benefit of this disclosure and its principles, various modifications and changes in form and detail can be made without departing from the principles and structures of the invention, which are, however, encompassed by the appended claims.
Claims (9)
1. The integral fault early warning method of the fire water system is characterized by comprising the following steps of:
step 1: the detection sensor acquires analog quantity data acquired by the detection sensor and transmits the analog quantity data to the edge computing gateway in a one-way mode;
step 2: the edge computing gateway receives data collected by the detection sensor;
and step 3: the method comprises the steps that an edge computing gateway obtains data collected by all detection sensors in a fire fighting water system, and the collected data are analyzed according to a multivariable CUSUM Control Chart method, so that risk early warning of the whole fire fighting water system is completed;
and 4, step 4: sending the risk early warning result to receiving equipment in a communication mode, wherein the receiving equipment comprises a mobile phone, a computer and an Internet of things data center;
and 5: and the data center of the Internet of things receives and stores the data.
2. The method according to claim 1, wherein in the step 3, the pre-warning of the whole fire fighting water system is performed by first acquiring historical data X of the whole fire fighting water system in a normal stateIC={X1,X2,X3,…,XnEach data variable XiIs represented as Xi=[Xi1 Xi2…Xim]TM represents the vector dimension of the data variable, in this case the number of sensors in the fire-fighting water system; historical mean data are obtained through calculationExpressed as:
next, a sample variance S is obtained, expressed as:
for sensor group data obtained over a new period of time, denoted as Y1,Y2,Y3,…,YtWherein each variable YiAre all m-dimensional vectors, Yi=[Yi1 Yi2…Yim]T(ii) a Acquiring the sensor group data in the periodMean, the mean of the data obtained finally is expressed as μ; and proposes the hypothesis:
in the MCUMSUM method, two variables s are set in an iterative manneri and CiRespectively expressed as:
where the parameter k is set by the allowable deviation of each sensor and the mean dataObtaining a sample variance S; by a variable si and CiObtaining a detection mean judgment bit ZiJudging the obtained detection mean value to be ZiAnd comparing the signal with a set value h to judge whether to give out early warning.
5. The fire water system overall fault early warning method according to claim 2, wherein in the step 3, if Z is obtainediIf the detection time is more than h, the state change of the fire fighting water system is considered to be large in the detection time, and early warning is given out; otherwise, the fire-fighting water system is considered to work stably.
6. An overall fault early warning system of a fire water system, wherein the system is based on the method of any one of claims 1-5, and the system comprises a detection sensor, an edge computing gateway and an internet of things data center; wherein the detection sensor is arranged in the fire-fighting water system; the edge computing gateway is connected with the detection sensors and can receive real-time data detected by the detection sensors; the edge computing gateway is also connected with the data center of the Internet of things.
7. The fire fighting water system as defined in claim 6, wherein the fire fighting water system comprises an automatic sprinkler system, a foam fire fighting system, a fire pool and water tank, and a pipeline, and the fire pool and water tank are connected with the automatic sprinkler system and the foam fire fighting system through the pipeline.
8. The fire water system overall fault early warning system according to claim 7, wherein the detection sensor comprises a hydraulic sensor and a liquid level sensor, wherein the hydraulic sensor is arranged at the junction and corner of the pipeline; the liquid level sensor is arranged at the fire pool and the water tank.
9. A fire water system global failure pre-warning system according to claim 8, wherein the edge gateway comprises a storage module, a processing module and a communication module; the processing module is used for processing the data collected by the detection sensor; the communication module is used for connecting the data center of the Internet of things and external equipment; the storage module is used for storing detection data acquired by the detection sensor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210113091.4A CN114664058B (en) | 2022-01-29 | 2022-01-29 | Overall fault early warning system and method for fire fighting water system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210113091.4A CN114664058B (en) | 2022-01-29 | 2022-01-29 | Overall fault early warning system and method for fire fighting water system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114664058A true CN114664058A (en) | 2022-06-24 |
CN114664058B CN114664058B (en) | 2023-08-18 |
Family
ID=82026217
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210113091.4A Active CN114664058B (en) | 2022-01-29 | 2022-01-29 | Overall fault early warning system and method for fire fighting water system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114664058B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB201216480D0 (en) * | 2011-09-19 | 2012-10-31 | Fisher Rosemount Systems Inc | Inferential process modeling,quality prediction and fault detection using multi-stage data segregation |
US20140067327A1 (en) * | 2011-05-03 | 2014-03-06 | China Real-Time Technology Co., Ltd. | Similarity curve-based equipment fault early detection and operation optimization methodology and system |
CN103646177A (en) * | 2013-12-16 | 2014-03-19 | 青岛理工大学 | Civil engineering structure damage early warning method considering temperature influence |
US20140266672A1 (en) * | 2013-03-15 | 2014-09-18 | Simplex Grinnell Lp | Real time control chart generation and monitoring of safety systems |
US20170276571A1 (en) * | 2016-03-24 | 2017-09-28 | Johnson Controls Technology Company | Systems and methods for fault detection and handling by assessing building equipment performance |
CN108897954A (en) * | 2018-06-29 | 2018-11-27 | 龙源(北京)风电工程技术有限公司 | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations |
CN109325310A (en) * | 2018-10-25 | 2019-02-12 | 山东科技大学 | A kind of bullet train intermittent fault detection method based on the multiple side's T control figure |
CN111122191A (en) * | 2019-12-05 | 2020-05-08 | 杭州哲达科技股份有限公司 | Equipment health alarm threshold setting method based on EWMA control |
CN111932102A (en) * | 2020-08-03 | 2020-11-13 | 南京航空航天大学 | Civil aircraft system risk early warning method based on dynamic control chart |
CN112330934A (en) * | 2020-10-28 | 2021-02-05 | 城安盛邦(北京)网络科技股份有限公司 | Artificial intelligence identification and study-judgment algorithm for fire alarm information |
CN113792972A (en) * | 2021-08-11 | 2021-12-14 | 上海至冕伟业科技有限公司 | Fire safety management method |
WO2022017059A1 (en) * | 2020-07-23 | 2022-01-27 | 华为技术有限公司 | Fire extinguishing system and fault determining method |
-
2022
- 2022-01-29 CN CN202210113091.4A patent/CN114664058B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140067327A1 (en) * | 2011-05-03 | 2014-03-06 | China Real-Time Technology Co., Ltd. | Similarity curve-based equipment fault early detection and operation optimization methodology and system |
GB201216480D0 (en) * | 2011-09-19 | 2012-10-31 | Fisher Rosemount Systems Inc | Inferential process modeling,quality prediction and fault detection using multi-stage data segregation |
US20140266672A1 (en) * | 2013-03-15 | 2014-09-18 | Simplex Grinnell Lp | Real time control chart generation and monitoring of safety systems |
CN103646177A (en) * | 2013-12-16 | 2014-03-19 | 青岛理工大学 | Civil engineering structure damage early warning method considering temperature influence |
US20170276571A1 (en) * | 2016-03-24 | 2017-09-28 | Johnson Controls Technology Company | Systems and methods for fault detection and handling by assessing building equipment performance |
CN108897954A (en) * | 2018-06-29 | 2018-11-27 | 龙源(北京)风电工程技术有限公司 | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations |
CN109325310A (en) * | 2018-10-25 | 2019-02-12 | 山东科技大学 | A kind of bullet train intermittent fault detection method based on the multiple side's T control figure |
CN111122191A (en) * | 2019-12-05 | 2020-05-08 | 杭州哲达科技股份有限公司 | Equipment health alarm threshold setting method based on EWMA control |
WO2022017059A1 (en) * | 2020-07-23 | 2022-01-27 | 华为技术有限公司 | Fire extinguishing system and fault determining method |
CN111932102A (en) * | 2020-08-03 | 2020-11-13 | 南京航空航天大学 | Civil aircraft system risk early warning method based on dynamic control chart |
CN112330934A (en) * | 2020-10-28 | 2021-02-05 | 城安盛邦(北京)网络科技股份有限公司 | Artificial intelligence identification and study-judgment algorithm for fire alarm information |
CN113792972A (en) * | 2021-08-11 | 2021-12-14 | 上海至冕伟业科技有限公司 | Fire safety management method |
Non-Patent Citations (1)
Title |
---|
温粉莲;: "一种混合模型的时序数据异常检测方法", 数字通信世界, no. 01 * |
Also Published As
Publication number | Publication date |
---|---|
CN114664058B (en) | 2023-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108490889B (en) | The safe big data data source method for generation of intelligent plant and device based on TE model | |
JP6647824B2 (en) | Error diagnosis system and error diagnosis method | |
CN105184386A (en) | Method for establishing abnormal event early warning system based on expert experience and historical data | |
WO2017051576A1 (en) | Plant operation system and plant operation method | |
US20150212506A1 (en) | Controller, manager, plant control system, and data processing method | |
CN113487140A (en) | Operation management platform and control method for intelligent construction equipment on building construction site | |
CN113340344B (en) | Hydraulic climbing mould intelligent monitoring control early warning system based on digital twin technology | |
CN112101743A (en) | Safety evaluation system for high-performance metal material processing workshop | |
JPH0954613A (en) | Plant facility monitor device | |
CN117072884A (en) | Monitoring and early warning system for natural gas and oil gas pipeline | |
CN114666361A (en) | Fire-fighting Internet of things-based water system overall fault detection system and method | |
CN114429308A (en) | Enterprise security risk assessment method and system based on big data | |
CN110288789B (en) | Building electric fire-fighting alarm device and control method thereof | |
CN117670028A (en) | Dust removal system risk dynamic assessment and grading early warning method based on Internet of things monitoring | |
JPH11161327A (en) | Method and device for diagnosing abnormality of process | |
CN114664058A (en) | Integral fault early warning system and method for fire water system | |
CN114613110A (en) | Fire water system fault detection early warning system and method based on fire-fighting Internet of things | |
CN116909235A (en) | Intelligent factory monitoring method, intelligent factory monitoring system and electronic equipment | |
CN116562739A (en) | Liquid chemical engineering wharf operation flow planning and dynamic monitoring system | |
CN111178693A (en) | Fire-fighting equipment management system based on two-dimensional code | |
CN114969068B (en) | Urban pressure pipe network real-time flow monitoring data analysis method and system | |
CN113684868B (en) | City utility tunnel early warning system | |
CN110533305A (en) | A kind of smelter work safety accident Synthetical prevention method | |
CN113869712A (en) | Intelligent system for large-scale industrial gas production | |
CN113991855A (en) | Performance monitoring and fault early warning method and system for initial operation stage of comprehensive energy system |
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 |