CN106482943A - A kind of boiler stop valve based on decision tree system closes failure method for early warning - Google Patents

Abstract

The invention discloses a kind of boiler stop valve based on decision tree system closes failure method for early warning, comprise the steps：Step (1), acquisition boiler room environment and boiler operating parameter data A, then obtain boiler stop valve closing failure marginal value B, set up stop valve and close failure error rate table T；Step (2)：Set up decision tree system, set up contradistinction system, decision tree system and contradistinction system are carried out logic and mates；Step (3)：Electronic sensor obtains real-time boiler stop valve and cuts out data transfer to decision tree system, obtains stop valve and closes failure high low value probability P；Step (4)：If P is more than 0.8, console provides alarm；Step (5)：Boiler staff is confirmed after obtaining the alarm that console sends, if it is confirmed that rear boiler stop valve closing failure and decision tree system misjudgment is then described, revises decision tree system.The present invention realizes the automatization judgement that boiler stop valve closes failure.

Description

A kind of boiler stop valve based on decision tree system closes failure method for early warning

Technical field

The invention belongs to early warning technology field, more particularly to a kind of boiler stop valve closing mistake based on decision tree system Clever method for early warning.

Background technology

Currently domestic each stop valve is closed failure early warning system and is provided with electronic sensor prompt system.Traditional electronics Fundamentals of Sensors are in the high low value that stop valve is closed failure, will be timely for the numerical value of each section by electronic sensor perception Feed back to central control system.By the picture and text prompting of central control system, work learns that boiler stop valve closes the high low value of failure.But Due to the corrosivity of the high temperature of generator tube, stove water, electronic sensor is caused with a certain degree of impact so that closing in stop valve Close and cause wrong estimate in failure value of feedback, or falsity occurs, led to the judgement causing boiler staff to produce mistake Major accident occurs.And the high electronic sensor of sensitivity is expensive, replacing is difficult, and is replaced as frequently as so that producing family ten The headache divided.So current domestic stop valve closes the stop valve closing mistake that failure early warning system cannot accurately react boiler The high low value of spirit.Most electronic sensor uses electrochemical principle to produce electrification to the free metal ion in water before this, leads to Cross the transmission of the signal of telecommunication to point out stop valve to close the high low value of failure.But it to be that underwater gold belongs to ion motion and enlivens that furnace temperature is too high Result is caused with certain interference.

Content of the invention

The purpose of the present invention is that and overcomes the deficiencies in the prior art, there is provided a kind of boiler main based on decision tree system Steam valve closes failure method for early warning, can immediate correction electronic sensor under circumstances error in data, remind boiler work The situation that personnel's stop valve closes failure closes failure situation so that staff obtains an accurate stop valve, to guarantee The operation of boiler normal table, to extend the life-span of the use of electronic sensor, reduces the maintenance cost of boiler, realizes boiler main Steam valve closes the automatization judgement of failure, accuracy of judgement, no longer needs artificial judgment, mitigates the labor intensity of staff.

To achieve these goals, the invention provides a kind of boiler stop valve closing failure based on decision tree system is pre- Alarm method, comprises the steps：

Step (1), obtain boiler room environment and boiler operating parameter data A, then obtain boiler stop valve closing failure and face Dividing value B, according to the mutual pace of learning in data A and marginal value BCorrespond to error rate table t, by the numerical value in error rate table t Set up stop valve after being quantified as the decimal between 0-1 and close failure error rate table T；

Step (2)：Failure error rate table T is closed as decision tree system skeleton according to the stop valve in step (1), sets up Decision tree system, obtains the historical data foundation comparison that staff's artificial judgment boiler stop valve closes the high low value of failure simultaneously System, decision tree system and contradistinction system is carried out logic and mates；

Step (3)：Real-time boiler stop valve is obtained by electronic sensor and closes data, and transmit to decision tree system, Obtain stop valve after decision tree system repetition training and close failure high low value probability P；

Step (4)：Decision tree system judges that stop valve closes the size of failure high low value probability P, if P is more than 0.8, Illustrate that failure in the closing of boiler stop valve, result is transferred to console by decision tree system, and console provides alarm；As Fruit P is less than 0.8, then explanation boiler stop valve is closed normally, and console will not provide alarm；

Step (5)：After boiler staff obtains the alarm that console sends, to boiler, actual stop valve closes feelings Condition is confirmed, if it is confirmed that rear boiler stop valve closes normal then explanation decision tree system misjudgment, now boiler work Correct result is inputed to contradistinction system by personnel, revises decision-making after now mating contradistinction system again with decision tree system logic Tree system；If it is confirmed that failure and decision tree system correct judgment is then described in rear boiler stop valve closing；

Step (6)：Repeat step (3)-(5), so constantly circulate and constantly revise decision tree system until decision tree system Accuracy of judgement, no longer needs staff's artificial judgment stop valve to close failure situation.

Further, in step (2), the formula of decision tree system meets：

Wherein：X_SFor feedback score, X_BHFor convolution constant, K_XFor the converse feedback number of plies, S_OFor vector convolution constant, K_OHIt is fixed Justice vector constant collection, f_pFor subset probability, b_HFor counts, K_hCount for error in judgement.

Beneficial effects of the present invention：The present invention can immediate correction electronic sensor under circumstances error in data, carry The situation that awake boiler staff's stop valve closes failure closes failure so that staff family obtains an accurate stop valve Situation, to guarantee the operation of boiler normal table, and to extend the life-span of the use of electronic sensor, the maintenance reducing boiler becomes This, realize the automatization judgement that boiler stop valve closes failure, accuracy of judgement, no longer needs artificial judgment, mitigates staff's Labor intensity.

Brief description

In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, acceptable Other accompanying drawings are obtained according to these accompanying drawings.

Fig. 1 is the flow chart of the embodiment of the present invention.

Specific embodiment

Below in conjunction with the accompanying drawings invention is further illustrated, but be not limited to the scope of the present invention.

Embodiment

As shown in figure 1, a kind of boiler stop valve based on decision tree system that the present invention provides closes failure method for early warning, Comprise the steps：

Step (1), obtain boiler room environment and boiler operating parameter data A, then obtain boiler stop valve closing failure and face Dividing value B, according to the mutual pace of learning in data A and marginal value BCorrespond to error rate table t, by the numerical value in error rate table t Set up stop valve after being quantified as the decimal between 0-1 and close failure error rate table T；

Boiler room environmental data includes：Boiler room size, has several spendable boilers, the species of boiler, use Time, energy supply type etc..Boiler operating parameter data includes furnace temperature, cigarette temperature, hydraulic pressure, vapour pressure, water inlet pump discharge, combustor Temperature, air channel data, stop valve etc..

Step (2)：Failure error rate table T is closed as decision tree system skeleton according to the stop valve in step (1), sets up Decision tree system, obtains the historical data foundation comparison that staff's artificial judgment boiler stop valve closes the high low value of failure simultaneously System, decision tree system and contradistinction system is carried out logic and mates；

Step (3)：Real-time boiler stop valve is obtained by electronic sensor and closes data, and transmit to decision tree system, Obtain stop valve after decision tree system repetition training and close failure high low value probability P；

Step (4)：Decision tree system judges that stop valve closes the size of failure high low value probability P, if P is more than 0.8, Illustrate that failure in the closing of boiler stop valve, result is transferred to console by decision tree system, and console provides alarm；As Fruit P is less than 0.8, then explanation boiler stop valve is closed normally, and console will not provide alarm；

Step (5)：After boiler staff obtains the alarm that console sends, to boiler, actual stop valve closes feelings Condition is confirmed, if it is confirmed that rear boiler stop valve closes normal then explanation decision tree system misjudgment, now boiler work Correct result is inputed to contradistinction system by personnel, revises decision-making after now mating contradistinction system again with decision tree system logic Tree system；If it is confirmed that failure and decision tree system correct judgment is then described in rear boiler stop valve closing；

Step (6)：Repeat step (3)-(5), so constantly circulate and constantly revise decision tree system until decision tree system Accuracy of judgement, no longer needs staff's artificial judgment stop valve to close failure situation.

In step (2), the formula of decision tree system meets：

Wherein：X_SFor feedback score, X_BHFor convolution constant, K_XFor the converse feedback number of plies, S_OFor vector convolution constant, K_OHIt is fixed Justice vector constant collection, f_pFor subset probability, b_HFor counts, K_hCount for error in judgement.

The present invention can immediate correction electronic sensor under circumstances error in data, remind the main vapour of boiler staff The situation that valve cuts out failure closes failure situation so that staff family obtains an accurate stop valve, to guarantee boiler just Often stable operation, to extend the life-span of the use of electronic sensor, reduces the maintenance cost of boiler, realizes boiler stop valve and closes Close the automatization judgement of failure, accuracy of judgement, no longer need artificial judgment, mitigate the labor intensity of staff.

Ultimate principle, principal character and the advantages of the present invention of the present invention have been shown and described above.The technology of the industry , it should be appreciated that the present invention is not restricted to the described embodiments, the simply explanation described in above-described embodiment and description is originally for personnel Invention principle, without departing from the spirit and scope of the present invention the present invention also have various changes and modifications, these change Change and improvement both falls within scope of the claimed invention.Claimed scope by appending claims and its Equivalent defines.

Claims (2)

1. a kind of boiler stop valve based on decision tree system closes failure method for early warning it is characterised in that comprising the steps：

Step (1), acquisition boiler room environment and boiler operating parameter data A, then obtain boiler stop valve closing failure marginal value B, according to the mutual pace of learning in data A and marginal value BCorrespond to error rate table t, by the numerical quantization in error rate table t Close failure error rate table T for setting up stop valve after the decimal between 0-1；

Step (2)：Failure error rate table T is closed as decision tree system skeleton according to the stop valve in step (1), sets up decision-making Tree system, the historical data simultaneously obtaining staff's artificial judgment boiler stop valve closing high low value of failure sets up control series System, decision tree system and contradistinction system is carried out logic and mates；

Step (3)：Real-time boiler stop valve is obtained by electronic sensor and closes data, and transmit to decision tree system, decision-making Obtain stop valve after tree system repeatedly training and close failure high low value probability P；

Step (4)：Decision tree system judges that stop valve closes the size of failure high low value probability P, if P is more than 0.8, illustrates Boiler stop valve is closed failure, and result is transferred to console by decision tree system, and console provides alarm；If P Less than 0.8, then explanation boiler stop valve is closed normally, and console will not provide alarm；

Step (5)：After boiler staff obtains the alarm that console sends, to boiler, actual stop valve closing situation is entered Row confirms, if it is confirmed that rear boiler stop valve is closed, and decision tree system misjudgment, now boiler staff are normally then described Correct result is inputed to contradistinction system, after now contradistinction system being mated with decision tree system logic again, revises decision tree system System；If it is confirmed that failure and decision tree system correct judgment is then described in rear boiler stop valve closing；

Step (6)：Repeat step (3)-(5), so constantly circulate and constantly revise decision tree system until decision tree system judgement Accurately, staff's artificial judgment stop valve is no longer needed to close failure situation.

2. a kind of boiler stop valve based on decision tree system according to claim 1 closes failure method for early warning, and it is special Levy and be, the formula of decision tree system meets in step (2)：

$\frac{{\mathrm{dX}}_S}{dt}=(1-f_p)b_H{X}_{BH}-k_h\left(\frac{\frac{X_S}{X_{BH}}}{K_X+\frac{X_S}{X_{BH}}}\right)\left(\frac{S_O}{K_{OH}+S_O}\right)X_{BH};$

Wherein：X_SFor feedback score, X_BHFor convolution constant, K_XFor the converse feedback number of plies, S_OFor vector convolution constant, K_OHFor definition to Amount constant collection, f_pFor subset probability, b_HFor counts, K_hCount for error in judgement.