CN102436252A - Process industry fault diagnosis method and system based on immune hazard theory - Google Patents

Abstract

The invention aims at using the characteristics of strong adaptability and self-learning capacity of an artificial immune system, overcoming the defects of long calculation time, high incorrect and missed report rate and the like of the existing artificial immune method, and applying an immune hazard theory to the fault diagnosis of a process industry. Compared with the existing artificial immune system, the invention provides a method for determining hazard signals and hazard rules and dividing hazardous areas, and additionally provides a fault diagnosis method based on the immune hazard theory. The process industry fault diagnosis method based on the immune hazard theory comprises a hazardous area dividing step, which is used for dividing the hazardous areas; an antibody generation step, which is used for generating antibodies according to history data in each hazardous area in the original fault samples; and a fault detection step, which is used for monitoring whether a process is faulted or not. The invention additionally provides a process industry fault diagnosis system based on the immune hazard theory.

Description

A kind of method for diagnosing faults and system of the process industry based on immune danger theory

Invention field

The present invention relates to a kind of method for diagnosing faults and system based on immune danger theory, it is mainly used in chemical process, oil refining process, the fault diagnosis field of process industries such as bio-pharmaceuticals process.

Background technology

A gordian technique of the stable operation of realization flow industry be exactly under the different working pattern to the unusual service condition that occurs can carry out accurately, reliable early diagnosis or early warning.In recent years, along with development of science and technology, in the modern production process, the system of application is increasingly sophisticated, and the equipment that relates to is specialized day by day, for continuous large batch of modern production process, is necessary to set up supervisory system more, in time finds and diagnose the reason that is out of order.From nineteen seventies, the research of process failure diagnosis is an emphasis of process industry research field just always.Fault diagnosis not only can guarantee the stability of production run, the generation of prevention serious accident effectively, timely; Can also, fault provide instruction after taking place; Help works engineer that fault is handled, repaired, the loss that effectively reduces fault and caused.

Through years development; Now main method for diagnosing faults roughly can be divided three classes from the diagnosis principle: based on the method for quantitative model, based on the method for qualutative model, based on the method for historical data; Typical method has the neural network method; Least square method, wavelet analysis method, PCA etc.Be Multivariable Statistical Methods to the more common method of the fault diagnosis of transient process in recent years; Its advantage is the generation that fast detecting is unusual; But the diagnosis accuracy with the contribution plot analytical approach is not high, and lacks the adaptive ability and the self-learning capability of the new fault of diagnosis.To this present situation, the artificial immune system that has the scholar to propose to have adaptivity and self-learning capability is incorporated into fault diagnosis field.

Artificial immune system is a kind of comprehensive intelligent system that relates to multidisciplinary field, and it organically combines immunology and engineering science, utilizes technology such as mathematics, computing machine to set up the immunologic mechanism model, and is applied to the aspects such as design, enforcement of engineering.In recent years, artificial immunity is introduced in fault diagnosis field gradually.But because conventional artificial immune system algorithm is very big owing to calculated amount, the element that relates to is more, has long problem computing time, and the wrong report that in process fault detection, might occur is failed to report.

To these problems, can other method be combined with artificial immune system on the one hand, set up the mixed fault diagnostic system of multi-method.On the other hand, artificial immune system itself being improved, is exactly wherein a kind of effective method based on the artificial immune system of danger theory.

The immunity danger theory is the many deficiencies to traditional artificial immune system, a new immune model of proposition.This model thinks that immune system is not to the nonego reaction, but to hazardous reaction.After the cell that is upset produced alarm signal, this type of macrophage antigen presenting cell was with near antigen capture and offer to lymphocyte.This signal itself can be set a hazardous location around oneself, and only the B cell in this scope just might produce the antibody of coupling antigen, experience immune response process.Do not match or not the cell in the hazardous location can not be upset.Danger theory no longer need be distinguished the notion of oneself and nonego as a kind of brand-new theoretical model, thereby and only need judge whether to bring loss to produce danger signal to body cell.It provides the thought of more effective deal with data for artificial immune system, promptly concentrate on dangerous, on the significant data.

Summary of the invention

The objective of the invention is to utilize the strong characteristics of artificial immune system adaptability and self-learning capability simultaneously; Overcome defectives such as existing artificial immunity method long wrong report rate of failing to report computing time is higher; Immune danger theory is applied to the fault diagnosis of process industry, and proposes the division methods of the definite and hazardous location of danger signal and dangerous rule.More existing artificial immune system, the division methods definite and hazardous location of danger signal that the present invention proposes and dangerous rule has been represented a kind of brand-new method for diagnosing faults based on immune danger theory.

According to an aspect of the present invention, a kind of method for diagnosing faults based on immune danger theory is provided, has it is characterized in that comprising:

Description of drawings

Fig. 1 has shown the process flow diagram of method according to an embodiment of the invention.

Fig. 2 has shown the process flow diagram that the hazardous location that method according to an embodiment of the invention adopted is divided.

Fig. 3 has shown the secondary continuous stir reactor schematic flow sheet that method according to an embodiment of the invention is used.

Fig. 4 has shown the SDG figure of the secondary continuous stir reactor flow process that method according to an embodiment of the invention is used.

Embodiment

The objective of the invention is to utilize the strong characteristics of artificial immune system adaptability and self-learning capability simultaneously, overcome defectives such as existing artificial immunity method long wrong report rate of failing to report computing time is higher, immune danger theory is applied to the fault diagnosis of process industry.More existing artificial immune system the present invention proposes the division methods of confirming to reach the hazardous location of danger signal and dangerous rule, and has proposed a kind of method for diagnosing faults based on immune danger theory.

To the fault diagnosis of process industry, as shown in Figure 1, method according to an embodiment of the invention comprises:

-SDG and HAZOP analytical procedure

Immune danger theory diagnostic system according to an embodiment of the invention can directly carry out SDG (signed digraph) and HAZOP (dangerous and operability analysis) analysis at step S101 to the original process flow process; At first analyze through SDG; Obtain the mutual relationship between the flow process variable; The hazard level of preliminary judgment variable, and obtain SDG figure.Pass through HAZOP again and analyze, the dangerous hidden danger that exists in the discovery flow process, and, judge danger classes through calculating Dow Chemical index and LOPA (protective seam analysis) analysis.HAZOP analyzes and can use other safe evaluation methods such as safety checklist method, FTA to replace in this step.

Definite step of-danger signal and dangerous rule

The Dow Chemical index and the LOPA analysis result that obtain according to step S101; Can confirm the dangerous hidden danger of technology and obtain the danger classes of variable at step S102; The variable that danger classes is higher is decided to be danger signal, and according to the characteristics and the HAZOP analysis result of variable, confirms dangerous rule; Reach the variable requirement that danger signal must satisfy, otherwise just think to have taken place fault.

-hazardous location partiting step

In case S102 has confirmed danger signal through step, get into step S103, be that the hazardous location is divided according to the SDG analysis result in the center with said danger signal.

According to a specific embodiment of the present invention as shown in Figure 2, this hazardous location partiting step further comprises:

1 makes the neighbouring relations matrix by SDG figure.Numerical value of each each row of row done adds and obtain:

C _i＝d _1i+d _2i+...d _ni，R _j＝d _j1+d _j2+...+d _jn (1)

D wherein _IjBe the element of the capable j row of adjacency matrix i, C _iFor row element with, R _jFor column element with.

2.1 confirm the hazardous location under each variable i.At first, make i=1.

2.2 judge whether danger signal of i, if i is that danger signal is then with its dangerous center as a hazardous location, to 2.3.Otherwise, calculate the affiliated hazardous location of i, according to SDG figure, with D to 3.1 _iRecord variable i calculates immediate hazardous location, SD downstream _iRecord variable i is to the distance of calculating center, immediate hazardous location downstream.

2.3 make i=i+1, to the next point of 2.2 inspections.

3.1 whether judgment variable i has link variable downwards, if do not have, i.e. and R _i=0, then explanatory variable i does not have the hazardous location of connection downwards, makes D _i=0, SD _i=0, to 4.1 steps.Otherwise explanatory variable i is at least 1 to the distance of calculating center, immediate hazardous location downstream, makes SD _i=1, to 3.2 steps, calculate the hazardous location that variable i connects downwards.

3.2.1 judgment variable i has several link variables downwards, if having only link variable, i.e. a R _i=1, then make i*=j, wherein j satisfies d _Ij=1, go on foot to 3.2.2.Otherwise link variable is greater than 1, to 3.3.1.

3.2.2 whether judge i* is danger signal, if danger signal, then i* is the center, hazardous location that meets the demands, and makes D _i=i* is to 4.1 steps.Otherwise, get into the 3.2.3 step.

Form loop 3.2.3 judge whether i to i*, perhaps i* does not have link variable downwards, if, i.e. i*=i or R _I*=0, make D _i=0, to 4.1 steps.Otherwise, get into the 3.2.4 step.

3.2.4 judgment variable i* has several link variables downwards, if having only link variable, i.e. a R _I*=1, make i*=j, wherein j satisfies d _I*j=1, go on foot to 3.2.6.Otherwise the link variable number is greater than 1, goes on foot to 3.2.5.

3.2.5 variable i * has a more than link variable downwards, makes j={j (1), j (2) ... .}, satisfy d _{I* (jk)}=1.Make i*=j (k*), wherein k* satisfies C _{J (k*)}=minC _jBe about to the minimum link variable of linking number as next variable, go on foot to 3.2.6.

3.2.6 obtain new link variable i*, the initial variable i distance of distance adds 1.Make SD _i=SD _i+ 1.To 3.2.2.

3.3.1R _i＞1, establish j*={j (1), j (2) ..., satisfy d _{I (jk)}=1.Make t=1, consider the feasible hazardous location of each j (t), go on foot to 3.3.2.

3.3.2 make i*=j (t), the possibility of investigating hazardous location under this branch road goes on foot to 3.3.3.

3.3.3 whether judge i* is danger signal, if danger signal, then i* is the center, hazardous location that meets the demands, and makes D _{I (t)}=i* goes on foot to 3.3.8.Otherwise, get into the 3.3.4 step.

Form loop 3.3.4 judge whether i to i*, perhaps i* does not have link variable downwards, if, i.e. i*=i or R _I*=0, make D _{I (t)}=0, go on foot to 3.3.8.Otherwise, get into the 3.3.5 step.

3.3.5 judgment variable i* has several link variables downwards, if having only link variable, i.e. a R _I*=1, make i*=j, wherein j satisfies d _I*j=1, go on foot to 3.3.7.Otherwise the link variable number is greater than 1, goes on foot to 3.3.6.

3.3.6 variable i * has a more than link variable downwards, makes j={j (1), j (2) ..., satisfy d _{I* (jk)}=1.Make i*=j (k*), wherein k* satisfies C _{J (k*)}=minC _jBe about to the minimum link variable of linking number as next variable, go on foot to 3.3.7.

3.3.7 obtain new link variable i*, the initial variable i distance of distance adds 1.Make SD _{I (t)}=SD _{I (t)}+ 1.To 3.3.3.

All calculated 3.3.8 judge whether all j (t), if calculated, i.e. t=R _iTo 4.1, otherwise consider next j (t), make t=t+1, go on foot to 3.3.2.

4.1 whether judgment variable i upwards has link variable, if do not have, i.e. and C _i=0, then explanatory variable i does not upwards have the hazardous location of connection, makes U _i=0, SU _i=0, to 5 steps.Otherwise explanatory variable i is at least 1 to the distance of calculating center, immediate hazardous location downstream, makes SU _i=1, to 3.2 steps, calculate the hazardous location that variable i connects downwards.

4.2.1 judgment variable i has several link variables downwards, if having only link variable, i.e. a C _i=1, then make i*=j, wherein j satisfies U _Ij=1, go on foot to 4.2.2.Otherwise link variable is greater than 1, to 4.3.1.

4.2.2 whether judge i* is danger signal, if danger signal, then i* is the center, hazardous location that meets the demands, and makes U _i=i* is to 5 steps.Otherwise, get into the 4.2.3 step.

Form loop 4.2.3 judge whether i to i*, perhaps i* does not have link variable downwards, if, i.e. i*=i or C _I*=0, make U _i=0, to 5 steps.Otherwise, get into the 4.2.4 step.

4.2.4 judgment variable i* has several link variables downwards, if having only link variable, i.e. a C _I*=1, make i*=j, wherein j satisfies U _I*j=1, go on foot to 4.2.6.Otherwise the link variable number is greater than 1, goes on foot to 4.2.5.

4.2.5 variable i * has a more than link variable downwards, makes j={j (1), j (2) ..., satisfy U _{I* (jk)}=1.Make i*=j (k*), wherein k* satisfies C _{J (k*)}=minC _jBe about to the minimum link variable of linking number as next variable, go on foot to 4.2.6.

4.2.6 obtain new link variable i*, the initial variable i distance of distance adds 1.Make SU _i=SU _i+ 1.To 4.2.2.

4.3.1C _i＞1, establish j*={j (1), j (2) ..., satisfy U _{I (jk)}=1.Make t=1, consider the feasible hazardous location of each j (t), go on foot to 4.3.2.

4.3.2 make i*=j (t), the possibility of investigating hazardous location under this branch road goes on foot to 4.3.3.

4.3.3 whether judge i* is danger signal, if danger signal, then i* is the center, hazardous location that meets the demands, and makes U _{I (t)}=i* goes on foot to 4.3.8.Otherwise, get into the 4.3.4 step.

Form loop 4.3.4 judge whether i to i*, perhaps i* does not have link variable downwards, if, i.e. i*=i or C _I*=0, make U _{I (t)}=0, go on foot to 4.3.8.Otherwise, get into the 4.3.5 step.

4.3.5 judgment variable i* has several link variables downwards, if having only link variable, i.e. a C _I*=1, make i*=j, wherein j satisfies U _I*j=1, go on foot to 4.3.7.Otherwise the link variable number is greater than 1, goes on foot to 4.3.6.

4.3.6 variable i * has a more than link variable downwards, makes j={j (1), j (2) ..., satisfy U _{I* (jk)}=1.Make i*=j (k*), wherein k* satisfies C _{J (k*)}=minC _jBe about to the minimum link variable of linking number as next variable, go on foot to 4.3.7.

4.3.7 obtain new link variable i*, the initial variable i distance of distance adds 1.Make SU _{I (t)}=SU _{I (t)}+ 1.To 4.3.3.

All calculated 4.3.8 judge whether all j (t), if calculated, i.e. t=C _iTo 5, otherwise consider next j (t), make t=t+1, go on foot to 4.3.2.

5 compare i apart from center, hazardous location, the upper reaches and hazardous location, downstream centre distance.If SD _i＜SU _i, Z _i=D _iIf SD _i＞SU _i, Z _i=U _iIf SD _i=SU _i, Z _i={ U _i, D _i.So far can confirm the hazardous location that variable i is affiliated, to 6 steps.

Whether 6 inspection i have calculated all variablees, if check out to 2.3, inspection down a bit.If all variablees all calculate completion, then the area dividing step is all over.

-data acquisition and processing

Immune danger theory diagnostic system according to an embodiment of the invention can directly be connected with production equipment; At step S201 (Fig. 1); Through such as PLC (Programmable Logic Controller), DCS (Distributed Control System (DCS)) and LIMS (LIMS) etc. gather required flow process variable data.Wherein known historical data is used for system initialization, sets up and confirms dangerous rule and produce original antibody, and real-time online data then is used for fault detection and diagnosis.All historical datas are introduced into step S202 and carry out the normalization processing by formula (1):

$X=0.5+\frac{x-\stackrel{\‾}{X}}{X_{\max }-X_{\min }}---\left(1\right)$

Wherein x is a real data,

X _MaxWith X _MinThe mean value of this variable data, maximal value and minimum value when being respectively nominal situation.

In according to one embodiment of present invention, data acquisition and treatment step can be used as another preposition step of carrying out before the method for embodiment of the present invention.

-generation antibody library

For the primary fault sample that after S202 step normalization, obtains,, confirm its failure mode and time at step S203; For the variable in each hazardous location; Get fault and introduce the data of back set time length, generate first generation antibody, note is made Ab_fault=[Ab ₁, Ab ₂..., Ab _n].The matrix that these antibody all are made up of the seasonal effect in time series data sample, Ab _iTime series for each variable in the same hazardous location.Each fault sample will generate several different first generation antibody according to different hazardous locations like this.First generation antibody of the same type generates a large amount of second generation antibody through step S204 by formula (2) variation and clone, has constituted antibody library.

$X*=\left\{\begin{array}{cc}\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_i{X}_i+b(X_c-X_d),& \underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}{a}_i=1...n>1\\ (1+\frac{b}{2}){\mathrm{<figure-callout\; id="1"\; label="X"\; filenames="HSA00000292471400021.png,HSA00000292471400031.png"\; state="\{\{state\}\}">X</figure-callout>}}_1& ...n=1\end{array}\right.---\left(2\right)$

Wherein n is the number of known this kind first generation antibody, X _iBe known first generation antibody, X* is the second generation antibody that generates through the variation clone.a _iBe the decimal at random in 0 to 1, b is the decimal at random between-1 to 1.C and d are the random integers between 1 to n.

Calculate the threshold value of every kind of fault type antibody again.

For two antibody (or antigen) of confirming, can adopt the diversity factor of Dynamic Time Warping algorithm computation antigen and antibody.The time series of at first getting identical variable also can use the straightforward procedure of formula (3) directly to calculate with DTW (Dynamic Time Warping) algorithm computation diversity factor:

${\mathrm{\&eta;}}_k=\frac{\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}|\mathrm{Ab}\left(i\right)-\mathrm{Ag}\left(i\right)|}{n}---\left(3\right)$

The diversity factor of calculating all variablees just can obtain the total variances degree vector of antigen and antibody:

η＝[η ₁，η ₂，…，η _n] (4)

Diversity factor in the calculating antibody storehouse between all antibody of the same type, the note be η (i, j).The threshold value of calculating each variable of the type antibody respectively is:

${\mathrm{threshold}}_k=\underset{1\&le;i\&le;\mathrm{<figure-callout\; id="1"\; label="n\; min"\; filenames="HSA00000292471400021.png,HSA00000292471400031.png"\; state="\{\{state\}\}">n</figure-callout>}}{\mathrm{<figure-callout\; id="1"\; label="max"\; filenames="HSA00000292471400021.png,HSA00000292471400031.png"\; state="\{\{state\}\}">max</figure-callout>}}\underset{}{\min }\underset{1\&le;j\&le;n,i\&NotEqual;j}{}\left|{\mathrm{\&eta;}}_k(i,j)\right|---\left(5\right)$

-utilize danger signal to carry out fault detect

The real time data that obtains through the S201 step was introduced into step S205 before carrying out fault diagnosis, carry out normalization by formula (1) after, obtain real-time detection data x _NewGet into step S206, utilize danger signal to carry out fault detect, whether break down by danger signal and dangerous rule monitoring flow process.

-utilize antibody library to carry out fault diagnosis

Break down in case detect affirmation at step S206, processing gets into step S207, and the variable of the data that detect constantly preceding set time length being accordinged to different hazardous locations generates different antigens respectively, and note is made Ag=[Ag ₁, Ag ₂..., Ag _n].The form of the antibody of identical hazardous location is identical in these antigens and the antibody library, the matrix of all being made up of the time series data sample of hazardous location internal variable, Ag _iTime series for each variable.

After antigen generates, handle the failure mode diagnosis that gets into step S208, utilize DTW algorithm or formula (6) to calculate the diversity factor of all antibody of identical hazardous location in antigen and the antibody library.

${\mathrm{\&eta;}}_k=\frac{\underset{i=1}{\overset{n}{\mathrm{\&Sigma;}}}|\mathrm{Ab}\left(i\right)-\mathrm{Ag}\left(i\right)|}{n}---\left(6\right)$

When each hazardous location all has antibody to calculate diversity factor less than corresponding threshold value, think that then fault is consistent with the type antibody.Otherwise promptly be judged as a kind of new fault.

The fault diagnosis result of refer step S208, the operator can carry out manual work diagnosis (S301), and is input to system, and system gets into step S209, and the result who accepts input is as final diagnostic result.

-antibody library upgrades

At step S203, with antigen as first generation antibody.Get into step S204 again, the type antibody is carried out clonal vaviation, upgrade the antibody in the antibody library, and upgrade the threshold value of this antibody by formula (5) by formula (2).

Embodiment:

The fault diagnosis of the reaction realistic model that has been applied to the secondary continuous stir reactor according to the method for the invention.

The flow process of secondary continuous stir reactor is as shown in Figure 3; This flow process is in continuous stir reactor R-1, to be mixed and be cooled to definite temperature (50 ℃) back by hot water in the uniform temperature (95 ℃) and cold water (40 ℃) to get into continuous stir reactor R-2; The flow relative fixed (60kg/h) of cold water, the flow of hot water is by the fluid level controller decision of R-1.After cooling, obtain confirming the chilled water of flow (360kg/h) and temperature (30 ℃), and regulate the liquid level in the R-2 through adding an amount of hot water (95 ℃).Two continuous stir reactors all have is with the chilled water of controlling to satisfy the liquid material temperature requirement in the still.

Monitored parameters comprises temperature T r1 and the liquid level Lr1 in the continuous stir reactor R-1, inlet cold water flow and temperature F101, T101, cold water flow and temperature F102; T102, rate of discharge and temperature F102, T102, the flow of chilled water and temperature F104; T104, the temperature T r2 of continuous stir reactor R-2 and liquid level Lr2, inlet hot water flow and temperature F201, T201; Rate of discharge and temperature F102, T102, the flow of chilled water and temperature F104, T103.

The fundamental purpose of this flow process is exactly in order to obtain confirming the water of flow and temperature.The controlling index of whole process main operating parameters and controller is as shown in table 1.

Table 1 nominal situation parameter is provided with

Operating parameter	Numerical value	Controlled target	Numerical value
				R-1 cold water flow	60±5kg/h	The R-1 temperature	50℃
Cold water temperature	40±2℃	The R-2 temperature	30℃
				The hot water temperature	95±2℃	The R-1 liquid level	50％
Cooling water temperature	30℃	The R-2 liquid level	50％
						The R-2 outlet temperature	360kg/h

At first carry out HAZOP analysis and SDG analysis according to step S101 flow.Analyze the dangerous hidden danger of this technological process of discovery and main dangerous matter sources through HAZOP.Analyze the relation that obtains between the SDG figure affirmation variable through SDG, as shown in Figure 4.

Get into step S102 again, confirm danger signal and dangerous rule.According to Dow Chemical Index for Calculation result and LOPA analysis result, find Tr1, Tr2, the harmful grade of Lr2 is higher, and these three variablees are decided to be danger signal.Because these three variablees are control variable, according to the HAZOP analysis result, the concrete numerical value of its variable and stability are all very crucial for flow process again.Therefore, these three danger signals are confirmed dangerous rule as follows:

$0.9*V_{\min }<{\tilde{V}}_i<1.1*V_{\max }$ $\left(7\right)$

$|{\tilde{V}}_i-{\tilde{V}}_{i-1}|<1.1*{|V_k-V_{k-1}|}_{\max }$

Wherein

Be the real time data value of danger signal, V _kHistorical data value for danger signal.Subscript i and k represent the time sequence number of variable.V _MinAnd V _MaxBe respectively the minimum value and the maximal value of danger signal historical data.

According to the SDG of secondary continuous stir reactor figure (see figure 4), confirm three danger signal: Tr1, Tr2, Lr2, again with all variablees according to danger signal step as shown in Figure 2, be divided into three hazardous locations.With T101 is example, and it is as shown in table 2 at first to make adjacency matrix.

Table 2 secondary continuous stir reactor fault diagnosis test result

Through calculating, be the hazardous location 1 at center with Tr1, comprise T101, T102, T103, T104, F101, F102, F103, F104, Tr1; With Tr2 is the hazardous location 2 at center, comprises T103, T201, T202, T203, F103, F201, F203, Tr2; With Lr2 is the hazardous location 3 at center, comprises F101, F102, Lr1, F103, F201, F202, Lr1, Lr2.

When carrying out preliminary analysis and planning, obtain the detection data of these all variablees through step S201, sampling time interval is 5 seconds.

The normal sample that will pass through in the historical data after S202 goes on foot normalization is brought formula (7) into, helps to confirm about dangerous regular details among the step S102.Get into step S202 again

In addition, F102 is too high the cold water flow, and the V-3 valve turns down; Each 2 groups of data of the malfunctioning three kinds of faults of LC-2 controller; Carry out normalization at step S202, near 10 sampling number certificates step S203 gets the fault introducing time again are according to the division of three hazardous locations; Generate three independently antibody respectively, and carry out variation and clone's generation antibody library of antibody at step S204.

Accomplish the initialization of fault diagnosis system like this, again real time data has been carried out fault detection and diagnosis after step S205 normalization.This instance has adopted 13 groups of real time data samples that method is verified altogether.

Be example with sample 1 at first, sample 1 is for slightly improving the sample that produces behind the cold water flow, and after S205 step normalization, the entering S206 step utilizes danger signal to carry out fault detect.The danger signal data that calculate all sampled points all satisfy dangerous rule, that is to say that this disturbance does not produce actual fault effects for the production of this technological process, so testing result think that this sample is a nominal situation.And that the method for diagnosing faults that utilizes other is easy to that this sample is diagnosed as the cold water flow is too high and report to the police.

Be example with sample 2 again, sample 2 is for significantly improving the fault sample that the cold water flow produces, after S205 step normalization; The entering S206 step utilizes danger signal to carry out fault detect, and after fault was introduced 15s, the danger signal data had exceeded the restriction range of dangerous rule; Think fault has taken place; Get into the S207 step by ten sampling number certificates before failure detection time,, generate 3 independently antigens according to the division of hazardous location.Through S208 step, utilize the diversity factor of antibody to calculate the tracing trouble kind again, find in 3 antigens and the too high antibody library of cold water flow 3 kinds of antibody diversity factoies less than the type fault threshold, and with other types antibody diversity factor all greater than its corresponding threshold.Therefore diagnostic result is the too high fault of cold water flow, and it is too high to confirm that through step S209 artificial diagnostic result is the cold water flow, gets into the S203 step, generates new antibodies by antigen.Through the S204 step, carry out the clone and the variation of antibody again, upgrade antibody library.

All fault diagnosis results of this instance are as shown in table 3.

Table 3 secondary continuous stir reactor fault diagnosis test result

Sequence number	Fault category	Detect time-delay	Diagnostic result	Computing time
						1	Normal *	-	Normally
2	1. the cold water flow is too high	15s	Fault	1	0.2458s
						3	1. the cold water flow is too high	15s	Fault	1	0.1640s
4	1. the cold water flow is too high	15s	Fault	1	0.1575s
						5	2.V-3 valve turns down	15s	Fault	2	0.1667s
6	2.V-3 valve turns down	15s	Fault	2	0.1626s
						7	2.V-3 valve turns down	15s	Fault	2	0.1595s
8	3.LC-2 controller is malfunctioning	300s	Fault	3	1.1324s
						9	3.LC-2 controller is malfunctioning	145s	Fault	3	0.2985s
10	3.LC-2 controller is malfunctioning	130s	Fault	3	0.3440s
						11	4.TC-2 controller is malfunctioning	255s	New fault	0.7584s
12	4.TC-2 controller is malfunctioning	90s	Fault	4	0.3105s
						13	4.TC-2 controller is malfunctioning	135s	Fault	4	0.4054s

* this normal sample does not destroy dangerous rule for slightly improving the sample that produces behind the cold water flow.

Should be understood that; In above narration and explanation to just explanation but not determinate of description that the present invention carried out; And like enclosed under the prerequisite of the present invention that claims limit not breaking away from, can carry out various changes, distortion and/or revise the foregoing description.

Claims (10)

1. method for diagnosing faults based on the process industry of immune danger theory is characterized in that comprising:

The hazardous location partiting step is used to divide the hazardous location;

Antibody generates step, generates antibody by the historical data in each said hazardous location in the primary fault sample;

Whether failure detection steps is used to monitor flow process and breaks down.

2. according to the method for diagnosing faults based on the process industry of immune danger theory of claim 1, it is characterized in that further comprising:

SDG and safety evaluation analytical procedure are used for the original process flow process is carried out corresponding analysis;

Danger signal is confirmed step with dangerous rule, is used for confirming danger signal and dangerous rule by said SDG and HAZOP analysis result;

Wherein said hazardous location partiting step further comprises: with said danger signal is that said hazardous location is divided according to the SDG analysis result in the center.

3. according to the method for diagnosing faults based on the process industry of immune danger theory of claim 2, it is characterized in that further comprising:

Antigen generates step, judges in said failure detection steps under the situation that the fault existence is arranged, and generates a plurality of antigens respectively with real time data in each hazardous location of schedule time length before the detection constantly of said failure detection steps,

The failure mode diagnosis algorithm utilizes said antigen and said antibody, judges the kind of fault.

4. according to the method for diagnosing faults based on the process industry of immune danger theory of claim 3, it is characterized in that further comprising:

Data acquisition and treatment step are gathered required flow process variable data, and said flow process variable data comprises historical data and said real time data, and said historical data comprises said original normal sample and said primary fault sample.

5. according to the method for diagnosing faults based on the process industry of immune danger theory of claim 4, it is characterized in that

Said SDG and safety evaluation analytical procedure comprise:

Carry out that SDG analyzes and from HAZOP analyze, based at least a analysis of selecting the analysis of safety checklist method and the analysis based on FTA,

Calculate the Dow Chemical index, and

Carry out LOPA and analyze,

Said danger signal confirms that with dangerous rule step comprises:

Thereby the hazard level of the judgment variable of analyzing with said Dow Chemical index and LOPA is as a result confirmed danger signal,

Confirm the dangerous regular of said danger signal with said HAZOP analysis result, and

Divide danger signal with said SDG and HAZOP analysis result.

6. fault diagnosis system based on the process industry of immune danger theory is characterized in that comprising:

The hazardous location classification apparatus is used to divide the hazardous location;

The antibody generating apparatus generates antibody by the historical data in each said hazardous location in the primary fault sample,

Whether failure detector is used to monitor flow process and breaks down.

7. according to the fault diagnosis system based on the process industry of immune danger theory of claim 6, it is characterized in that further comprising:

The safety evaluation analytical equipment is used for the original process flow process is carried out SDG and reached the safety evaluation analysis;

Danger signal is confirmed device with dangerous rule, is used for confirming danger signal and dangerous rule by said SDG and HAZOP analysis result;

Wherein said hazardous location classification apparatus further comprises: with said danger signal is that said hazardous location is divided according to the SDG analysis result in the center.

8. according to the fault diagnosis system based on the process industry of immune danger theory of claim 7, it is characterized in that further comprising:

The antigen generating apparatus is judged under the situation that the fault existence is arranged at said failure detector, generates a plurality of antigens respectively with real time data in each hazardous location of schedule time length before the detection constantly of said failure detector,

The failure mode diagnostic device utilizes said antigen and said antibody, judges the kind of fault.

9. according to Claim 8 the fault diagnosis system based on the process industry of immune danger theory is characterized in that further comprising:

Data acquisition and treating apparatus are gathered required flow process variable data, and said flow process variable data comprises historical data and said real time data, and said historical data comprises said original normal sample and said primary fault sample.

10. according to the fault diagnosis system based on the process industry of immune danger theory of claim 9, it is characterized in that

Said safety evaluation analytical equipment comprises:

Be used for carrying out that SDG analyzes and the part of at least a analysis analyzing, select based on the analysis of safety checklist method and based on the analysis of FTA from HAZOP,

Be used to calculate the part of Dow Chemical index, and

Carry out the part that LOPA analyzes,

Said danger signal confirms that with dangerous rule device comprises:

Thereby the hazard level of the judgment variable of analyzing with said Dow Chemical index and LOPA is as a result confirmed the part of danger signal,

Confirm the part of the dangerous rule of said danger signal with said HAZOP analysis result, and

Divide the part of danger signal with said SDG and HAZOP analysis result.

Images