CN106596090A - Decision-making-tree-system-based early warning method for boiler steam valve fault - Google Patents

Abstract

The invention discloses a decision-making-tree-system-based early warning method for a boiler steam valve fault. The method comprises: step one, boiler room environment and boiler operation parameter data A are obtained and then a boiler steam value fault critical value B is obtained, and a steam valve fault error rate table T is established; step two, a decision-making tree system and a comparison system are established and logic matching is carried out on the decision-making tree system and the comparison system; step three, an electronic sensor obtains real-time boiler steam valve data and transmits the data to the decision-making tree system to obtain a steam valve fault high-low valve probability P; step four, if the P is larger than 0.8, a central console carries out alarming and prompting; and step five, a boiler worker obtains the alarming and promoting information sent out by the central console and then carries out determination; if a fault occurs at the boiler steam value after determination, the decision-making tree system makes wrong judgment and is corrected. Therefore, automatic determination of a boiler steam valve fault is realized.

Description

A kind of Boiler Steam valve fault early warning method based on decision tree system

Technical field

The invention belongs to early warning technology field, more particularly to a kind of Boiler Steam valve failure based on decision tree system is pre- Alarm method.

Background technology

Current domestic each steam valve fault early warning system is provided with electronic sensor prompt system.Traditional electronic sensor Device principle is, by the high low value of steam valve failure, to be perceived by electronic sensor and timely feed back to the numerical value of each section Central control system.The high low value of Boiler Steam valve failure is learnt in work by the picture and text prompting of central control system.But due to generator tube High temperature, the corrosivity of stove water, a certain degree of impact is caused on electronic sensor so that make in steam valve failure value of feedback Into wrong estimate, or there is falsity, cause major accident occur with the judgement for causing boiler staff to produce mistake.And The high electronic sensor of sensitivity it is expensive, replacing is difficult, and is replaced as frequently as so that producing family's very headache.So at present Domestic steam valve fault early warning system cannot accurately react the high low value of steam valve failure of boiler.Most electronics before this Sensor produces electrification to the free metal ion in water using electrochemical principle, points out steam valve by the transmission of the signal of telecommunication The high low value of failure.But it is that underwater gold belongs to that ion motion is active to cause certain interference to result that furnace temperature is too high.

The 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 based on decision tree system steams Steam valve fault early warning method, can immediate correction electronic sensor under circumstances error in data, remind boiler staff The situation of steam valve failure so that staff obtains an accurate steam valve failure condition, guarantees boiler normal table Operation, to extend the life-span for using of electronic sensor, reduce boiler maintenance cost, realize Boiler Steam valve failure from Dynamicization judges that 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 Steam valve fault pre-alarming side based on decision tree system Method, comprises the steps：

Step (1), acquisition boiler room environment and boiler operating parameter data A, then obtain Boiler Steam valve fault critical B, according to the mutual pace of learning in data A and marginal value BCorrespondence goes out error rate table t, by the numerical quantization in error rate table t For steam valve failure error rate table T is set up after the decimal between 0-1；

Step (2)：According to steam valve failure error rate table T in step (1) as decision tree system skeleton, decision-making is set up Tree system, while the historical data for obtaining the high low value of staff's artificial judgment Boiler Steam valve failure sets up contradistinction system, will Decision tree system carries out logic with contradistinction system and matches；

Step (3)：Real-time Boiler Steam valve data are obtained by electronic sensor, and is transmitted to decision tree system, decision-making The high low value probability P of steam valve failure is obtained after tree system repeatedly training；

Step (4)：Decision tree system judges the size of the high low value probability P of steam valve failure, if P is more than 0.8, illustrates Boiler Steam valve breaks down, and result is transferred to console by decision tree system, and console provides alarm；If P is less than 0.8, then illustrate that Boiler Steam valve is normal, console will not provide alarm；

Step (5)：After boiler staff obtains the alarm that console sends, boiler actual steam valve situation is entered Row confirms that, if it is confirmed that rear Boiler Steam valve normally then illustrates decision tree system misjudgment, now boiler staff will just Really result inputs to contradistinction system, corrects decision tree system after now matched contradistinction system with decision tree system logic again； The decision tree system correct judgment that then illustrate if it is confirmed that rear Boiler Steam valve breaks down；

Step (6)：Repeat step (3)-(5), so constantly circulation constantly corrects decision tree system until decision tree system Accuracy of judgement, no longer needs staff's artificial judgment Boiler Steam valve failure condition.

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 Adopted 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 of awake boiler staff steam valve failure so that staff family obtains an accurate steam valve failure condition, comes Guarantee the operation of boiler normal table, to extend the life-span for using of electronic sensor, reduce the maintenance cost of boiler, realize pot The automatization judgement of stove steam valve failure, accuracy of judgement no longer need artificial judgment, mitigate the labor intensity of staff.

Description of the drawings

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 Accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with Other accompanying drawings are obtained according to these accompanying drawings.

Flow charts of the Fig. 1 for the embodiment of the present invention.

Specific embodiment

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

Embodiment

As shown in figure 1, a kind of Boiler Steam valve fault early warning method based on decision tree system that the present invention is provided, including Following steps：

Step (1), acquisition boiler room environment and boiler operating parameter data A, then obtain Boiler Steam valve fault critical B, according to the mutual pace of learning in data A and marginal value BCorrespondence goes out error rate table t, by the numerical quantization in error rate table t For steam valve failure error rate table T is set up after the decimal between 0-1；

Boiler room environmental data includes：Boiler room size, has several boilers that can be used, the species of boiler, use Time, energy supply type etc..Boiler operating parameter data include：Furnace temperature, cigarette temperature, hydraulic pressure, vapour pressure, water inlet pump discharge, burning Machine temperature, air channel data, steam valve etc..

Step (2)：According to steam valve failure error rate table T in step (1) as decision tree system skeleton, decision-making is set up Tree system, while the historical data for obtaining the high low value of staff's artificial judgment Boiler Steam valve failure sets up contradistinction system, will Decision tree system carries out logic with contradistinction system and matches；

Step (3)：Real-time Boiler Steam valve data are obtained by electronic sensor, and is transmitted to decision tree system, decision-making The high low value probability P of steam valve failure is obtained after tree system repeatedly training；

Step (4)：Decision tree system judges the size of the high low value probability P of steam valve failure, if P is more than 0.8, illustrates Boiler Steam valve breaks down, and result is transferred to console by decision tree system, and console provides alarm；If P is less than 0.8, then illustrate that Boiler Steam valve is normal, console will not provide alarm；

Step (5)：After boiler staff obtains the alarm that console sends, boiler actual steam valve situation is entered Row confirms that, if it is confirmed that rear Boiler Steam valve normally then illustrates decision tree system misjudgment, now boiler staff will just Really result inputs to contradistinction system, corrects decision tree system after now matched contradistinction system with decision tree system logic again； The decision tree system correct judgment that then illustrate if it is confirmed that rear Boiler Steam valve breaks down；

Step (6)：Repeat step (3)-(5), so constantly circulation constantly corrects decision tree system until decision tree system Accuracy of judgement, no longer needs staff's artificial judgment Boiler Steam valve failure condition.

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 Adopted 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 boiler staff's steam The situation of valve failure so that staff family obtains an accurate steam valve failure condition, guarantees boiler normal table Operation, to extend the life-span for using of electronic sensor, reduces the maintenance cost of boiler, realizes the automatic of Boiler Steam valve failure Change and judge, accuracy of judgement no longer needs artificial judgment, mitigates the labor intensity of staff.

Ultimate principle, principal character and the advantages of the present invention of the present invention has been shown and described above.The technology of the industry Personnel 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 this The principle of invention, of the invention without departing from the spirit and scope of the present invention also to have various changes and modifications, these changes Change and improvement is both fallen within scope of the claimed invention.The claimed scope of the invention by appending claims and its Equivalent is defined.

Claims (2)

1. a kind of Boiler Steam valve fault early warning method based on decision tree system, it is characterised in that comprise the steps：

Step (1), acquisition boiler room environment and boiler operating parameter data A, then obtain Boiler Steam valve fault critical B, root Mutual pace of learning according to data A and marginal value BCorrespondence goes out error rate table t, is 0-1 by the numerical quantization in error rate table t Between decimal after set up steam valve failure error rate table T；

Step (2)：According to steam valve failure error rate table T in step (1) as decision tree system skeleton, decision tree system is set up System, while the historical data for obtaining the high low value of staff's artificial judgment Boiler Steam valve failure sets up contradistinction system, by decision-making Tree system carries out logic with contradistinction system and matches；

Step (3)：Real-time Boiler Steam valve data are obtained by electronic sensor, and is transmitted to decision tree system, decision tree system The high low value probability P of steam valve failure is obtained after system repetition training；

Step (4)：Decision tree system judges the size of the high low value probability P of steam valve failure, if P is more than 0.8, illustrates boiler Steam valve breaks down, and result is transferred to console by decision tree system, and console provides alarm；If P is less than 0.8, Then illustrate that Boiler Steam valve is normal, console will not provide alarm；

Step (5)：After boiler staff obtains the alarm that console sends, boiler actual steam valve situation is carried out really Recognize, if it is confirmed that rear Boiler Steam valve normally then illustrates decision tree system misjudgment, now boiler staff correctly will tie Fruit inputs to contradistinction system, corrects decision tree system after now matched contradistinction system with decision tree system logic again；If After confirmation Boiler Steam valve break down then illustrate decision tree system correct judgment；

Step (6)：Repeat step (3)-(5), so constantly circulation constantly corrects decision tree system until decision tree system judges Accurately, no longer need staff's artificial judgment Boiler Steam valve failure condition.

2. a kind of Boiler Steam valve fault early warning method based on decision tree system according to claim 1, its feature exist In in step (2), the formula of decision tree system meets：

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

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.