CN104933249A - Ship instrument verification period determination method and system - Google Patents

Abstract

The invention relates to a ship instrument verification period determination method and system. Specific to the characteristic of large ship instrument verification amount, a Chi-square distribution model is established according to the instrument verification qualification situation of each batch; a judgment on whether or not an existing verification period is reasonable is made with a hypothesis testing method; and a corresponding adjusting method is provided. The verification period of instruments is adjusted reasonably, so that the technical problem of hidden danger to the accuracy and reliability of equipment performance caused by over-heavy verification task, cost increase and overlong verification period due to over-short verification period and high verification frequency in the prior art is solved. Meanwhile, the problems that a practical verification time interval is inconsistent with a specified verification period and that verification data is difficult to count and analyze since the instruments are under the influences of navigational duty and repair are solved. Through adoption of the model based on Chi-square distribution, specific reliability models of the instruments under verification do not need to be known, and certain universality is achieved.

Description

A kind of naval vessel instrument calibration cycle determination method and system

Technical field

The present invention relates to naval vessel instrument periodic verification technical field, particularly relate to a kind of naval vessel instrument calibration cycle determination method and system.

Background technology

Naval vessel being assembled with in a large number for the instrument of monitoring state, for ensureing that instrument and meter can normally play a role, must regularly examining and determine it.According to national measurement technical specification, determine that one of the cardinal rule in instrument calibration cycle determines the calibration interval according to the feature of instrument own, performance requirement and service condition.But the calibration interval of existing naval vessel instrument and meter generally adopt the method for estimation, and the calibration interval are about decided to be 1 year or half a year mostly.The immobilization of assay cycle is adopted to be with the problem of serving: calibration interval too short meeting causes the overweight and cost of verification task to increase because the calibrating frequency is high; Calibration interval are long, and that can give equipment performance brings hidden danger accurately and reliably.And naval vessel instrument and meter is subject to the impact of working environment, request for utilization, the calibration interval also should take corresponding change.

Naval vessel instrument is by the impact of navigational duty and maintenance in addition, and calibration interval of the actual calibrating time interval and regulation are also inconsistent, for the statistical study of calibrating data brings difficulty.

Summary of the invention

Technical matters to be solved by this invention is for the deficiencies in the prior art, provides a kind of naval vessel instrument calibration cycle determination method and system.

The technical scheme that the present invention solves the problems of the technologies described above is as follows: a kind of naval vessel instrument calibration cycle determination method, comprises the steps: to set up card side's distributed model according to original calibrating data; Whether the existing calibration interval are reasonable to utilize the hypothesis testing method of population distribution to judge according to card side's distributed model, if rationally, keep the existing calibration interval, if unreasonable, then calculate minimum regulation time, according to minimum regulation time, the existing calibration interval are adjusted.

The invention has the beneficial effects as follows: the present invention is directed to the feature that naval vessel instrument calibration amount is large, card side's distributed model is established according to the instrument calibration Qualification of every batch, and utilize the method for test of hypothesis whether rationally to judge the existing calibration interval, and propose corresponding method of adjustment.The calibration interval of Reasonable adjustment instrument of the present invention, solve that the calibration interval in prior art are too short, the calibrating frequency is high and cause the overweight and cost of verification task to increase, calibration interval are long, can give the technical matters bringing hidden danger accurately and reliably of equipment performance, solve instrument simultaneously and cause the calibration interval of the actual calibrating time interval and regulation by the impact of navigational duty and maintenance and inconsistent, the problem of the statistical study difficulty of calibrating data.The model that the present invention is based on the distribution of card side, without the need to knowing the concrete reliability model of tested instrument, has certain versatility.

On the basis of technique scheme, the present invention can also do following improvement.

Further, being implemented as follows of card side's distributed model is set up according to original calibrating data:

Same type and calibration interval identical instrument, have N to criticize in predetermined amount of time and wait to examine and determine, i-th batch of metered quantity is n _i, expect that qualification rate is P ₀, the qualified quantity of the expectation often criticized is e _i, then

e _i＝n _i*P ₀

If the i-th batch of qualified quantity of reality is g _i, then qualified in i-th batch of censorship instrument and underproof quantity is obeyed card side and is distributed according to (1) formula is approximate, degree of freedom v=1;

${\mathrm{\ξ}}_i=\frac{{(g_i-e_i)}^2}{e_i}+\frac{{\[(n_i-g_i)-(n_i-e_i)\]}^2}{n_i-e_i}=\frac{{(g_i-e_i)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}---\left(1\right)$

The beneficial effect of above-mentioned further scheme is adopted to be: to achieve nonparametric model, without the need to knowing the reliability model that instrument is concrete and parameter thereof.

According to the additive property of card side's distribution, the distribution of same obedience card side, degree of freedom v=N, the side's of card distributed model is as shown in (2) formula;

$\underset{i=1}{\overset{N}{\Σ}}{\mathrm{\ξ}}_i=\underset{i=1}{\overset{N}{\Σ}}\[\frac{{(g_i-e_i)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}\]---\left(2\right).$

The beneficial effect of above-mentioned further scheme is adopted to be: the sample size adding statistical study.

Further, described n _ispan for being more than or equal to 50, g _ispan for being more than or equal to 5, if g _ibe less than 5, the calibrating data of this batch of calibrating data and adjacent batch are merged.

The beneficial effect of above-mentioned further scheme is adopted to be: the reliability ensureing assay.

Further, the hypothesis testing method of population distribution is utilized to judge existing calibration interval T according to card side's distributed model ₀whether be reasonably implemented as: utilize the hypothesis testing method of population distribution to criticize the total actual assay approval rate of instrument to N and verify with whether expectation assay approval rate P0 is consistent.

The beneficial effect of above-mentioned further scheme is adopted to be: hypothesis testing method than simple thresholding method more comprehensively.

Further, according to card side's distributed model utilize the hypothesis testing method of population distribution to N criticize the total actual assay approval rate of instrument with expect assay approval rate P0 whether consistent verify be implemented as:

Former supposition H ₀: suppose that the actual assay approval rate that N criticizes instrument total is consistent with the assay approval rate P0 of expectation;

Under certain level of significance α, inquire about chi-square distribution table according to α and N and obtain χ ²(α, N); If then suppose to set up, without the need to adjusting existing calibration interval T ₀if, then hypothesis is false, then adjust existing calibration interval T ₀.

Further, if N criticizes the assay approval rate of instrument and the assay approval rate P of expectation ₀inconsistent, adjust existing calibration interval T ₀, be implemented as follows:

Solve actual assay approval rate mean value calculate i-th crowd of qualified quantity g' estimated _i, adjust g ' with time variable Δ t _iobtain Δ g' _i;

If then extend existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀+ Δ t ₀;

If then shorten existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀-Δ t ₀.

Further, the assay approval quantity g ' estimated under the existing calibration interval for i-th time is calculated _icircular as follows:

Based on the hypothesis that crash rate λ is identical: then

Wherein, T ₀for the existing calibration interval, T _iit is i-th actual calibrating time interval; P _ibe i-th actual assay approval rate; P _i' be the assay approval rate estimated under the existing calibration interval for i-th time;

Then ${P_i}^{\′}=1-\left(\frac{1-P_i}{T_i}\right)T_0$

The assay approval quantity g ' estimated under the existing calibration interval for i-th time _ibe calculated as follows:

${g_i}^{\′}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i{T}_0$

Wherein, n _ibe i-th batch of metered quantity;

G ' is adjusted with time variable Δ t _iobtain Δ g ' _i, ${\mathrm{\Δg}}_i^{,}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i(T_0\±\mathrm{\Δ}t),$

Wherein, Δ t=kt ₀, t ₀for a certain constant;

If then extend existing calibration interval T ₀, will k=1,2,3 ... bring formula (2) into, and whether checking meets former supposition H ₀, meet former supposition H until find ₀minimum k value, then new calibration interval T=T ₀+ kt ₀;

If then shorten existing calibration interval T ₀, will k=1,2,3 ... bring formula (2) into, and whether checking meets former supposition H ₀, meet former supposition H until find ₀minimum k value, then new calibration interval T=T ₀-kt ₀.

Another technical scheme that the present invention solves the problems of the technologies described above is as follows: a kind of naval vessel instrument calibration cycle certainty annuity, comprises MBM, detection module and adjusting module:

Described MBM, it is for setting up card side's distributed model according to original calibrating data;

Described detection module, for utilizing the hypothesis testing method of population distribution to judge according to card side's distributed model, whether the existing calibration interval are reasonable for it, if rationally, then keep the existing calibration interval, if unreasonable, call adjusting module;

Described adjusting module, it, for then calculating minimum regulation time, adjusts the existing calibration interval according to minimum regulation time.

Accompanying drawing explanation

Fig. 1 is the instrument calibration cycle determination method process flow diagram of naval vessel described in the embodiment of the present invention;

Fig. 2 is the instrument calibration cycle of naval vessel described in embodiment of the present invention certainty annuity block diagram.

Embodiment

Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.

As shown in Figure 1, a kind of naval vessel instrument calibration cycle determination method, comprises the steps.

The first step, sets up card side's distributed model according to original calibrating data.

Particularly, being implemented as follows of card side's distributed model is set up according to original calibrating data:

Same type and calibration interval identical instrument, in predetermined amount of time, (can be 1 year) has N to criticize to wait to examine and determine, and i-th batch of metered quantity is n _i, expect that qualification rate is P ₀, the qualified quantity of the expectation often criticized is e _i, then

e _i＝n _i*P ₀

If the i-th batch of qualified quantity of reality is g _i, then qualified in i-th batch of censorship instrument and underproof quantity is obeyed card side and is distributed according to (1) formula is approximate, degree of freedom v=1;

${\mathrm{\ξ}}_i=\frac{{(g_i-e_i)}^2}{e_i}+\frac{{\[(n_i-g_i)-(n_i-e_i)\]}^2}{n_i-e_i}=\frac{{(g_i-e_i)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}---\left(1\right)$

According to the additive property of card side's distribution, the distribution of same obedience card side, degree of freedom v=N, the side's of card distributed model is as shown in (2) formula;

$\underset{i=1}{\overset{N}{\Σ}}{\mathrm{\ξ}}_i=\underset{i=1}{\overset{N}{\Σ}}\[\frac{{(g_i-e_i)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}\]---\left(2\right).$

Wherein, described n _ispan for being more than or equal to 50, g _ispan for being more than or equal to 5, if g _ibe less than 5, the calibrating data of this batch of calibrating data and adjacent batch are merged.

Second step, whether the existing calibration interval are reasonable to utilize the hypothesis testing method of population distribution to judge according to card side's distributed model, if rationally, keep the existing calibration interval, if unreasonable execution the 3rd step.

Particularly, former supposition H ₀: suppose that the actual assay approval rate that N criticizes instrument total is consistent with the assay approval rate P0 of expectation; Under certain level of significance α (representative value 0.05), inquire about chi-square distribution table according to α and N and obtain χ ²(α, N); If then suppose to set up, without the need to adjusting existing calibration interval T ₀if, then hypothesis is false, then adjust existing calibration interval T ₀.

3rd step, calculates minimum regulation time, adjusts the existing calibration interval according to minimum regulation time.

Particularly, if N criticizes the assay approval rate of instrument and the assay approval rate P of expectation ₀inconsistent, adjust existing calibration interval T ₀, be implemented as follows:

Solve actual assay approval rate mean value calculate i-th crowd of qualified quantity g ' estimated _i, adjust g ' with time variable Δ t _iobtain Δ g ' _i;

If then extend existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀+ Δ t ₀;

If then shorten existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀-Δ t ₀.

Wherein, the assay approval quantity g ' estimated under the existing calibration interval for i-th time is calculated _icircular as follows:

Based on the hypothesis that crash rate λ is identical: then

Wherein, T ₀for the existing calibration interval, T _iit is i-th actual calibrating time interval; P _ibe i-th actual assay approval rate; P _i' be the assay approval rate estimated under the existing calibration interval for i-th time;

Then ${P_i}^{\′}=1-\left(\frac{1-P_i}{T_i}\right)T_0$

The assay approval quantity g ' estimated under the existing calibration interval for i-th time _ibe calculated as follows:

${g_i}^{\′}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i{T}_0$

Wherein, n _ibe i-th batch of metered quantity;

G ' is adjusted with time variable Δ t _iobtain Δ g ' _i, ${\mathrm{\Δg}}_i^{,}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i(T_0\±\mathrm{\Δ}t),$

Wherein, Δ t=kt ₀, t ₀for a certain constant (representative value is 3 months or 6 months);

If then extend existing calibration interval T ₀, will k=1,2,3 ... bring formula (2) into, and whether checking meets former supposition H ₀, meet former supposition H until find ₀minimum k value, then new calibration interval T=T ₀+ kt ₀;

If then shorten existing calibration interval T ₀, will k=1,2,3 ... bring formula (2) into, and whether checking meets former supposition H ₀, meet former supposition H until find ₀minimum k value, then new calibration interval T=T ₀-kt _0.

As shown in Figure 2, a kind of naval vessel instrument calibration cycle certainty annuity, comprises MBM, detection module and adjusting module: described MBM, and it is for setting up card side's distributed model according to original calibrating data; Described detection module, for utilizing the hypothesis testing method of population distribution to judge according to card side's distributed model, whether the existing calibration interval are reasonable for it, if rationally, then keep the existing calibration interval, if unreasonable, call adjusting module; Described adjusting module, it, for then calculating minimum regulation time, adjusts the existing calibration interval according to minimum regulation time.

The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (10)

1. a naval vessel instrument calibration cycle determination method, is characterized in that, comprises the steps:

Card side's distributed model is set up according to original calibrating data; Whether the existing calibration interval are reasonable to utilize the hypothesis testing method of population distribution to judge according to card side's distributed model, if rationally, keep the existing calibration interval, if unreasonable, then calculate minimum regulation time, according to minimum regulation time, the existing calibration interval are adjusted.

2. a kind of naval vessel instrument calibration cycle determination method and system according to claim 1, is characterized in that, sets up being implemented as follows of card side's distributed model according to original calibrating data:

Same type and calibration interval identical instrument, have N to criticize in predetermined amount of time and wait to examine and determine (N=1,2,3...), i-th batch of metered quantity is n _i, expect that qualification rate is P ₀, the qualified quantity of the expectation often criticized is e _i, then

e _i＝n _i*P ₀

If the i-th batch of qualified quantity of reality is g _i, then qualified in i-th batch of censorship instrument and underproof quantity is obeyed card side and is distributed according to (1) formula is approximate, degree of freedom v=1;

${\mathrm{\ξ}}_i=\frac{{(g_i-e_i)}^2}{e_i}+\frac{{\[(n_i-g_i)-(n_i-e_i)\]}^2}{n_i-e_i}=\frac{{(g_i-e_i)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}---\left(1\right)$

According to the additive property of card side's distribution, the distribution of same obedience card side, degree of freedom v=N, the side's of card distributed model is as shown in (2) formula;

$\underset{i=1}{\overset{N}{\Σ}}{\mathrm{\ξ}}_i=\underset{i=1}{\overset{N}{\Σ}}\[\frac{{\left(g_i-e_i\right)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}\]---\left(2\right).$

3. a kind of naval vessel instrument calibration cycle determination method according to claim 2, is characterized in that, described n _ispan for being more than or equal to 50, g _ispan for being more than or equal to 5, if g _ibe less than 5, the calibrating data of this batch of calibrating data and adjacent batch are merged.

4. a kind of naval vessel instrument calibration cycle determination method according to claim 2, is characterized in that, utilize the hypothesis testing method of population distribution to judge existing calibration interval T according to card side's distributed model ₀whether be reasonably implemented as: utilize the hypothesis testing method of population distribution to criticize the total actual assay approval rate of instrument to N and verify with whether expectation assay approval rate P0 is consistent.

5. a kind of naval vessel instrument calibration cycle determination method according to claim 4, it is characterized in that, according to card side's distributed model utilize the hypothesis testing method of population distribution to N criticize the total actual assay approval rate of instrument with expect assay approval rate P0 whether consistent verify be implemented as:

Former supposition H ₀: suppose that the actual assay approval rate that N criticizes instrument total is consistent with the assay approval rate P0 of expectation;

Under certain level of significance α, inquire about chi-square distribution table according to α and N and obtain χ ²(α, N); If then suppose to set up, without the need to adjusting existing calibration interval T ₀if, then hypothesis is false, then adjust existing calibration interval T ₀.

6. a kind of naval vessel instrument calibration cycle determination method according to claim 5, is characterized in that, if N criticizes the assay approval rate of instrument and the assay approval rate P of expectation ₀inconsistent, adjust existing calibration interval T ₀, be implemented as follows:

Solve actual assay approval rate mean value calculate i-th crowd of qualified quantity g ' estimated _i, adjust g ' with time variable Δ t _iobtain Δ g ' _i;

If then extend existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀+ Δ t ₀;

If then shorten existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀-Δ t ₀.

7. a kind of naval vessel instrument calibration cycle determination method according to claim 6, is characterized in that, calculate the assay approval quantity g ' estimated under the existing calibration interval for i-th time _icircular as follows:

Based on the hypothesis that crash rate λ is identical: then

Wherein, T ₀for the existing calibration interval, T _iit is i-th actual calibrating time interval; P _ibe i-th actual assay approval rate; P _i' be the assay approval rate estimated under the existing calibration interval for i-th time;

Then ${P_i}^{\′}=1-\left(\frac{1-P_i}{T_i}\right)T_0$

The assay approval quantity g ' estimated under the existing calibration interval for i-th time _ibe calculated as follows:

${g_i}^{\′}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i{T}_0$

Wherein, n _ibe i-th batch of metered quantity;

G ' is adjusted with time variable Δ t _iobtain ${\mathrm{\Δg}}_i^{,}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i(T_0\±\mathrm{\Δ}t),$

Wherein, Δ t=kt ₀, t ₀for a certain constant;

If $\stackrel{\‾}{P}\≥P_0,$ Then extend existing calibration interval T ₀, will ${\mathrm{\Δg}}_i^{,}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i(T_0+{\mathrm{kt}}_0),k=1,$ 2,3 ... bring formula (2) into, and whether checking meets former supposition H ₀, meet former supposition H until find ₀minimum k value, then new calibration interval T=T ₀+ kt ₀;

If $\stackrel{\&OverBar;}{P}<P_0,$ Then shorten existing calibration interval T ₀, will ${\mathrm{\&Delta;g}}_i^{,}=n_i-\left(\frac{1-P_i}{T_i}\right)n_i(T_0-{\mathrm{kt}}_0),k=1,$ 2,3 ... bring formula (2) into, and whether checking meets former supposition H ₀, meet former supposition H until find ₀minimum k value, then new calibration interval T=T ₀-kt ₀.

8. a naval vessel instrument calibration cycle certainty annuity, is characterized in that, comprises MBM, detection module and adjusting module:

Described MBM, it is for setting up card side's distributed model according to original calibrating data;

Described detection module, for utilizing the hypothesis testing method of population distribution to judge according to card side's distributed model, whether the existing calibration interval are reasonable for it, if rationally, then keep the existing calibration interval, if unreasonable, call adjusting module;

Described adjusting module, it, for calculating minimum regulation time, adjusts the existing calibration interval according to minimum regulation time.

9. a kind of naval vessel instrument calibration cycle certainty annuity according to claim 8, is characterized in that, card side's distributed model that described MBM carries out following process is set up:

Same type and calibration interval identical instrument, have N to criticize in predetermined amount of time and wait to examine and determine, i-th batch of metered quantity is n _i, expect that qualification rate is P ₀, the qualified quantity of the expectation often criticized is e _i, then

e _i＝n _i*P ₀

If the i-th batch of qualified quantity of reality is g _i, then qualified in i-th batch of censorship instrument and underproof quantity is obeyed card side and is distributed according to (1) formula is approximate, degree of freedom v=1;

${\mathrm{\&xi;}}_i=\frac{{\left(g_i-e_i\right)}^2}{e_i}+\frac{{\&lsqb;\left(n_i-g_i\right)-\left(n_i-e_i\right)\&rsqb;}^2}{n_i-e_i}=\frac{{\left(g_i-e_i\right)}^2}{e_i}+\frac{{\left(g_i-e_i\right)}^2}{n_i-e_i}---\left(1\right)$

According to the additive property of card side's distribution, the distribution of same obedience card side, degree of freedom v=N, the side's of card distributed model is as shown in (2) formula;

$\underset{i=1}{\overset{N}{\&Sigma;}}{\mathrm{\&xi;}}_i=\underset{i=1}{\overset{N}{\&Sigma;}}\&lsqb;\frac{{(g_i-e_i)}^2}{e_i}+\frac{{(g_i-e_i)}^2}{n_i-e_i}\&rsqb;---\left(2\right).$

10. a kind of naval vessel instrument calibration cycle certainty annuity according to claim 8, it is characterized in that, described detection module carries out the detection of following process, judges that whether the existing calibration interval are reasonable:

Former supposition H ₀: suppose that the actual assay approval rate that N criticizes instrument total is consistent with the assay approval rate P0 of expectation;

Under certain level of significance α, inquire about chi-square distribution table according to α and N and obtain χ ²(α, N); If then suppose to set up, without the need to adjusting existing calibration interval T ₀if, then hypothesis is false, then adjust existing calibration interval T ₀;

Described adjusting module carries out the adjustment of following process, makes to meet former supposition H ₀:

Solve actual assay approval rate mean value calculate i-th crowd of qualified quantity g ' estimated _i, adjust g ' with time variable Δ t _iobtain Δ g ' _i;

If then extend existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _i; Bring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀+ Δ t ₀;

If then shorten existing calibration interval T ₀, by the qualified quantity Δ g ' that i-th crowd is estimated _ibring formula (2) into, and whether checking meets former supposition H ₀, adjustment Δ t is until find and meet former supposition H ₀minimum delta t value, then new calibration interval T=T ₀-Δ t ₀.