CN-122014219-A - Safety production monitoring method and device based on industrial Internet of things

CN122014219ACN 122014219 ACN122014219 ACN 122014219ACN-122014219-A

Abstract

The invention relates to the technical field of industrial Internet of things, in particular to a safety production monitoring method and device based on the industrial Internet of things, wherein the method comprises the steps of judging the kick risk based on the volume of a mud pit and the pressure of a casing in an analysis period, and determining an oscillation sign; the method comprises the steps of extracting and analyzing fluctuation characteristics of riser pressure in a period to determine underground working condition stability coefficients and further divide underground abnormal working conditions, extracting intrusion characteristics based on slurry inlet and outlet flow and inlet and outlet density, integrating oscillation marks in the period, underground working condition stability coefficients and intrusion characteristics to construct comprehensive risk indexes, dividing risk grades, determining hydraulic health measures based on hydraulic control oil pressure, leakage flow and BOP instructions in a management period, integrating the comprehensive risk indexes in the management period, and updating closing speed reference values. According to the invention, through multi-source data fusion analysis and self-adaptive control strategy, accurate early warning of well control risk and dynamic optimization of closing speed of the blowout preventer are realized.

Inventors

Wu Zuxu
LIN KAI
WU SHILI
XIU HONGMING
LI TIEGANG

Assignees

富利恒自动化工程技术(北京)有限公司

Dates

Publication Date: 20260512
Application Date: 20260319

Claims (10)

1. The safety production monitoring method based on the industrial Internet of things is characterized by comprising the following steps of: judging the well kick risk based on the mud pit volume and the casing pressure in the analysis period, and determining an oscillation mark; Extracting and analyzing fluctuation characteristics of the periodical riser pressure to determine a stability coefficient of the underground working condition, and dividing the underground abnormal working condition; Extracting intrusion features based on mud inlet and outlet flow rates and inlet and outlet densities; the oscillation marks in the analysis period, the underground working condition stability coefficient and the intrusion characteristic are fused to construct a comprehensive risk index, and risk grades are divided; a hydraulic health metric is determined based on the hydraulic control oil pressure, the leak flow, and the BOP command during the management cycle, and the closing speed reference value is updated in conjunction with the integrated risk index during the management cycle.
2. The industrial internet of things-based safety production monitoring method according to claim 1, wherein the 1 second sampling period is used for calculating the volume change amount deltav of the mud pit and the pressure change amount deltap of the casing pipe every second; Setting a volume change rate threshold Vth and a pressure change rate threshold Pth, and counting the times NV that DeltaV is greater than Vth and the times NP that DeltaP is greater than Pth in an analysis period; If the NV is larger than or equal to a preset abnormal threshold value and the NP is larger than or equal to the preset abnormal threshold value, the kick risk of the current analysis period is judged to be a kick high risk, and an oscillation mark is set to be 2, if the NV is larger than or equal to the preset abnormal threshold value and the NP is smaller than the preset abnormal threshold value, the kick risk of the current analysis period is judged to be a volume abnormal leading risk, and the oscillation mark Fg is set to be 1, if the NV is smaller than the preset abnormal threshold value and the NP is larger than or equal to the preset abnormal threshold value, the kick risk of the current analysis period is judged to be a pressure abnormal leading risk, and the oscillation mark Fg is set to be 0.
3. The industrial internet of things-based safety production monitoring method according to claim 2, wherein an average value Pta and a standard deviation Pts of the riser pressure in the analysis period are calculated, and then a pressure fluctuation intensity coefficient sf=pts/Pta is determined; Performing fast Fourier transform on the riser pressure sequence in the analysis period, calculating the power spectrum density of the riser pressure sequence, searching a frequency point with the maximum power spectrum amplitude in a target frequency band, marking the frequency point as fd, recording the corresponding power spectrum amplitude PSD of the frequency point, and further determining a pulsation significant coefficient Sp=min (1, PSD/(PSDn multiplied by 3)); the pressure fluctuation intensity coefficient and the pulsation significant coefficient are fused, and a downhole working condition stability coefficient C is constructed, wherein C=1- (c1×min (1, sf/sf 0) +c2×Sp); Wherein c1 is a pressure fluctuation intensity weight, c2 is a pulsation significant weight, c1+c2=1, psdn is a preset background noise baseline, and sf0 is a preset fluctuation intensity threshold.
4. The industrial internet of things-based safety production monitoring method according to claim 3, wherein the underground abnormal conditions are divided based on a condition stability coefficient C, if C is greater than or equal to j1, the underground abnormal conditions in the current analysis period are judged to be normal conditions, if C is greater than or equal to j2 and less than or equal to j1, the underground abnormal conditions in the current analysis period are judged to be low-risk conditions, and if C is less than j2, the underground abnormal conditions in the current analysis period are judged to be high-risk conditions; Wherein j1 is a first preset stability threshold, and j2 is a second preset stability threshold.
5. The industrial internet of things-based safety production monitoring method according to claim 4, wherein an inlet and outlet flow difference Δf of each sampling period in an analysis period is calculated, and the number Nf of sampling periods in which the inlet and outlet flow difference is greater than a preset overflow threshold Fth in the analysis period is counted, so as to determine an overflow characteristic coefficient kf=min (1, nf/n 1); Calculating the inlet and outlet density difference delta rho of each sampling period in the analysis period, and counting the number Nd of sampling periods with delta rho smaller than a preset density reduction threshold value rhoth in the analysis period so as to determine a density reduction characteristic coefficient Kd=min (1, nd/n 1); fusing the overflow characteristic coefficient with the density-decreasing characteristic coefficient to obtain an intrusion characteristic Ci, wherein Ci=β1×Kf+β2×Kd; where β1 is an overflow feature weight, β2 is a density drop feature weight, β1+β2=1, and n1 is a preset number threshold.
6. The industrial internet of things-based safety production monitoring method according to claim 5, wherein an oscillation flag Fg, a downhole condition stability coefficient C and an intrusion feature Ci in an analysis period are constructed to have a comprehensive risk index Rt, rt=w1×fg+w2×c+w3×ci; The risk level is divided according to the comprehensive risk index Rt, if Rt is smaller than r1, the current analysis period is judged to be low risk, if Rt is larger than or equal to r1 and smaller than or equal to r2, the current analysis period is judged to be medium risk, and if Rt is larger than r2, the current analysis period is judged to be high risk; Wherein r1 is a first preset risk threshold, r2 is a second preset risk threshold, and w1, w2 and w3 are weight coefficients.
7. The industrial Internet of things-based safety production monitoring method of claim 6, wherein the analysis period working conditions are divided according to BOP instructions, if BOP instructions exist in the current analysis period, the current analysis period working conditions are divided into dynamic working conditions, otherwise, the current analysis period is divided into steady-state working conditions; For an analysis period which is a stable working condition in a management period, calculating the average value Pavg of the hydraulic control oil pressure and the standard deviation Pstd of the hydraulic control oil pressure in the analysis period, taking (1-Pstd/Pavg) as a pressure stability coefficient of the analysis period, calculating the average value of the pressure stability coefficient in the management period as the pressure stability coefficient of the current management period, and marking as eta P; determining a steady-state health index Hs, hs=a1×ηp+a2× (1- ηq) according to the pressure stability coefficient ηp and the leakage severity coefficient ηq; wherein Qwarn is a preset early warning leakage flow, a1 is a pressure stabilizing weight, a2 is a first leakage weight, a1+a2=1.
8. The industrial internet of things-based safety production monitoring method of claim 7, wherein for each BOP command in the management cycle, starting at the BOP command issue time and ending at the BOP command execution completion, a dynamic evaluation window is formed, wherein in the dynamic evaluation window, a time Tr from the BOP command issue to the pressure reaching the target value is calculated, and a pressure response anomaly coefficient Rey, rey = min (1, max (0) (Tr-Tt))/(α×tt)) is calculated, and simultaneously, a leakage flow average value Qavgj in the dynamic evaluation window is calculated, and a leakage severity index Lj, lj = min (1, qavgj/Qwarn) in the dynamic evaluation window is calculated; determining a dynamic health index Ds, ds=b1×rey+b2× (1-Lj) according to the pressure response anomaly coefficient Rey and the leakage severity index Lj; Determining a hydraulic health metric D, d=γ1×hs+γ2×ds, from the steady state health index Hs and the dynamic health index Ds; where Tt is the rated rise time, b1 is the pressure response weight, b2 is the second leakage weight, b1+b2=1, γ1 is the steady state weight, γ2 is the dynamic weight, γ1+γ2=1, and α is the preset adjustment coefficient.
9. The industrial internet of things-based safety production monitoring method of claim 8, wherein an average value Ravg of the integrated risk indexes of each analysis period in a management period is calculated, and the closing speed reference value Vbn of the next management period is updated by fusing the hydraulic health metric D: if Ravg is less than r1, vbn=v1× (0.6+0.4×d); If Ravg is equal to or greater than r1 and equal to or less than r2, vbn=v2× (0.6+0.4×d); if Ravg is greater than r2, vbn=v3× (0.6+0.4×d); wherein v1 is a first preset closing speed reference value, v2 is a second preset closing speed reference value, and v3 is a third preset closing speed reference value.
10. The safety production monitoring device based on the industrial internet of things, which is applied to the safety production monitoring method based on the industrial internet of things as claimed in any one of claims 1 to 9, is characterized by comprising the following steps: The well kick analysis unit is used for judging the well kick risk based on the mud pit volume and the casing pressure in the analysis period and determining an oscillation mark; The working condition dividing unit is used for extracting and analyzing fluctuation characteristics of the periodical riser pressure to determine an underground working condition stability coefficient and further divide underground abnormal working conditions; an intrusion feature determination unit for extracting intrusion features based on the mud gate flow rate, the gate density; the risk dividing unit is used for fusing the oscillation mark, the underground working condition stability coefficient and the intrusion characteristic in the analysis period to construct a comprehensive risk index and dividing risk grades; And the reference updating unit is used for determining the hydraulic health measurement based on the hydraulic control oil pressure, the leakage flow and the BOP command in the management period and integrating the comprehensive risk index in the management period to update the closing speed reference value.

Description

Safety production monitoring method and device based on industrial Internet of things Technical Field The invention relates to the technical field of industrial Internet of things, in particular to a safety production monitoring method and device based on the industrial Internet of things. Background The offshore oil drilling platform has a severe working environment and extremely high well control risk. The blowout preventer system is used as key equipment for guaranteeing drilling safety, and the timeliness and reliability of emergency locking control of the blowout preventer system are directly related to the safety of a platform and personnel. The traditional blowout preventer is controlled by adopting a fixed parameter or simple threshold alarming mode, and has the problems of lag response, high false alarm rate, incapability of adapting to complex working condition changes and the like. In addition, the existing control strategy is difficult to effectively fuse multisource monitoring data, so that early recognition capability of abnormal working conditions such as kick, lost circulation and the like is insufficient, and a closing strategy cannot be dynamically optimized according to the health state of a hydraulic system, so that excessive equipment wear or untimely emergency response is easily caused. Therefore, an intelligent emergency locking control method capable of fusing multi-source information and having self-adaption capability is needed. Disclosure of Invention The invention aims to provide a safety production monitoring method and device based on industrial Internet of things, which are used for solving at least one of the problems in the prior art. In order to achieve the above purpose, the invention adopts the following technical scheme: a safety production monitoring method based on industrial Internet of things comprises the following steps: judging the well kick risk based on the mud pit volume and the casing pressure in the analysis period, and determining an oscillation mark; Extracting and analyzing fluctuation characteristics of the periodical riser pressure to determine a stability coefficient of the underground working condition, and dividing the underground abnormal working condition; Extracting intrusion features based on mud inlet and outlet flow rates and inlet and outlet densities; the oscillation marks in the analysis period, the underground working condition stability coefficient and the intrusion characteristic are fused to construct a comprehensive risk index, and risk grades are divided; a hydraulic health metric is determined based on the hydraulic control oil pressure, the leak flow, and the BOP command during the management cycle, and the closing speed reference value is updated in conjunction with the integrated risk index during the management cycle. Further, calculating the volume change delta V of the mud pit and the pressure change delta P of the casing every second by taking 1 second as a sampling period; Setting a volume change rate threshold Vth and a pressure change rate threshold Pth, and counting the times NV that DeltaV is greater than Vth and the times NP that DeltaP is greater than Pth in an analysis period; If the NV is larger than or equal to a preset abnormal threshold value and the NP is larger than or equal to the preset abnormal threshold value, the kick risk of the current analysis period is judged to be a kick high risk, and an oscillation mark is set to be 2, if the NV is larger than or equal to the preset abnormal threshold value and the NP is smaller than the preset abnormal threshold value, the kick risk of the current analysis period is judged to be a volume abnormal leading risk, and the oscillation mark Fg is set to be 1, if the NV is smaller than the preset abnormal threshold value and the NP is larger than or equal to the preset abnormal threshold value, the kick risk of the current analysis period is judged to be a pressure abnormal leading risk, and the oscillation mark Fg is set to be 0. Further, calculating an average value Pta and a standard deviation Pts of the riser pressure in the analysis period, and further determining a pressure fluctuation intensity coefficient sf=Pts/Pta; Performing fast Fourier transform on the riser pressure sequence in the analysis period, calculating the power spectrum density of the riser pressure sequence, searching a frequency point with the maximum power spectrum amplitude in a target frequency band, marking the frequency point as fd, recording the corresponding power spectrum amplitude PSD of the frequency point, and further determining a pulsation significant coefficient Sp=min (1, PSD/(PSDn multiplied by 3)); the pressure fluctuation intensity coefficient and the pulsation significant coefficient are fused, and a downhole working condition stability coefficient C is constructed, wherein C=1- (c1×min (1, sf/sf 0) +c2×Sp); Wherein c1 is a pressure fluctuation intensity weight, c2 is a pulsation si