Overground pipe gallery risk early warning method based on multi-dimensional data fusion

Abstract

The invention relates to the technical field of pipe gallery risk early warning, in particular to an overground pipe gallery risk early warning method based on multi-dimensional data fusion. Comprising the following steps: establishing a plurality of monitoring sub-areas according to pipe rack equipment parameters, and setting an inspection strategy according to all the monitoring sub-areas; acquiring a monitoring data packet and an inspection data packet of each monitoring sub-region according to a preset monitoring time node; generating a risk early warning value of each monitoring sub-region according to a preset risk diagnosis model, and judging whether an early warning instruction is generated or not according to all the risk early warning values; multi-dimensional data such as daily inspection risk data of the port overground pipe gallery, operation monitoring data collected by a sensor, historical construction data of the pipe gallery and the like are subjected to fusion processing, multi-dimensional correlation factors related to the risk are covered, early warning is carried out on potential risks of the port overground pipe gallery in time, and operation safety of the port overground pipe gallery is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of pipeline corridor risk warning, and in particular to a ground pipeline corridor risk warning method based on multi-dimensional data fusion. Background Art

[0002] The port above-ground pipeline corridor refers to a pipeline corridor system built above the ground in the port area, which is used to centrally lay and manage various pipelines (such as oil pipelines, natural gas pipelines, chemical pipelines, water supply pipelines, etc.). It is an important part of the port infrastructure, mainly used to transport liquids, gases or other media, and support the port's logistics and industrial production activities.

[0003] At present, the port's ground pipeline corridor is exposed to the external environment and is vulnerable to corrosion, wind disasters, etc. The risk monitoring of the port's ground pipeline corridor is mainly carried out through manual inspections, video monitoring or analysis of sensor-collected operating data. The data from different systems have not been effectively integrated, making it difficult to comprehensively analyze risks and establish an effective early warning mechanism. Summary of the invention

[0004] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a risk warning method for ground pipeline corridors based on multi-dimensional data fusion, aiming to improve the risk warning accuracy of port ground pipeline corridors and ensure the safe operation of port ground pipeline corridors.

[0005] In some embodiments of the present application, multi-dimensional data such as daily inspection risk data of the port's ground pipeline corridor, operation monitoring data collected by sensors, and historical construction data of the pipeline corridor are integrated and processed to cover multi-dimensional correlation factors related to risks, so as to provide timely warnings of potential risks of the port's ground pipeline corridor and ensure the safe operation of the port's ground pipeline corridor.

[0006] In some embodiments of the present application, by analyzing environmental meteorological factors, multiple disturbance scenarios are constructed, and by dynamically adjusting the risk warning strategies under each disturbance scenario, the probability and severity of various risks under specific meteorological conditions are accurately predicted, thereby avoiding disturbances to the risk diagnosis model due to environmental factors and improving the risk warning accuracy and maintenance efficiency of the port's ground pipeline corridor.

[0007] In some embodiments of the present application, a method for early warning of risks of an above-ground pipe gallery based on multi-dimensional data fusion is provided, comprising: Establish multiple monitoring sub-areas based on the equipment parameters of the tunnel, and set inspection strategies based on all monitoring sub-areas; Acquire monitoring data packets and inspection data packets of each monitoring sub-area according to the preset monitoring time node; Generate risk warning values ​​for each monitoring sub-area based on the preset risk diagnosis model, and determine whether to generate warning instructions based on all risk warning values; When multiple monitoring sub-areas are set, they include: Establish a monitoring sub-area sequence A, A=(a1, a2…a i …a n ), where a i is the ith monitoring sub-area; n is the number of monitoring sub-areas.

[0008] In some embodiments of the present application, when a risk diagnosis model is preset, it includes: Establish a fusion sub-model and set multiple risk characteristic indicators; Establish a diagnostic sub-model based on all risk characteristic indicators; Generate multiple disturbance evaluation indicators based on the historical environmental data of the pipeline corridor, and generate multiple disturbance scenarios based on all disturbance indicators; Establish a disturbance scenario sequence B, B=(b1, b2…b i …b m ), where b i is the ith disturbance scenario; m is the number of disturbance scenarios; Generate correction sub-strategies for each disturbance scenario, and establish a correction sub-model based on all correction sub-strategies; A risk diagnosis model is established based on the fusion sub-model, the diagnosis sub-model and the correction sub-model.

[0009] In some embodiments of the present application, when multiple monitoring sub-areas are set, the following is also included: According to the monitoring sub-area sequence A, set a i Monitor sub-areas for the target; Obtain historical construction data and equipment data of the target monitoring sub-area to set the potential risk value c of the target monitoring sub-area; Set the potential risk value of each target monitoring sub-area in turn; Establish a potential risk value series C, C=(c1,c2…c i …c n ), where c i is the potential risk value of the ith monitoring sub-area; n is the number of monitoring sub-areas; According to the potential risk value sequence C, the compensation coefficient of each monitoring sub-area is set; Establish compensation coefficient sequence K, K=(k1,k2…k i …k n ), where k i is the compensation coefficient of the ith monitoring sub-area; n is the number of monitoring sub-areas.

[0010] In some embodiments of the present application, when setting the compensation coefficient of each monitoring sub-area, it includes: The first potential risk value interval (C1, C2), the second potential risk value threshold (C2, C3) and the third potential risk value threshold (C3, C4) are preset, and C1 <C2<C3<C4; If c i When in the preset first potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K1; If c i When in the preset second potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K2; If c i When in the preset third potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K3; and K3 <K2<K1<1。

[0011] In some embodiments of the present application, when setting the potential risk value c of the target monitoring sub-area, it includes: c=e1*Q1*[ η 1i *s i ]+e2*Q2*[ η2i *w i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ1 is the number of construction risk indicators; η 1i is the influencing factor of the i-th construction risk index; s i is the reference value of the i-th construction risk index of the target monitoring sub-area; θ2 is the number of equipment evaluation indicators; η 2i is the influencing factor of the i-th equipment evaluation index; w i is the reference value of the evaluation index of the i-th device in the target monitoring sub-area.

[0012] In some embodiments of the present application, when generating the risk warning value of each monitoring sub-area, it includes: According to the monitoring sub-area sequence A, set a i is the sub-region to be diagnosed; Obtain monitoring data packets and inspection data packets of the sub-area to be diagnosed at the current monitoring time node; Generate a feature data packet of the sub-area to be diagnosed at the current monitoring time node according to the preprocessing result of the monitoring data packet and the inspection data packet by the fusion sub-model; Generate a risk warning value f of the sub-area to be diagnosed at the current monitoring time node according to the diagnosis sub-model and the feature data packet; Generate the risk warning value of each monitoring sub-area at the current monitoring time node in sequence; Establish a risk warning value series F, F=(f1, f2…f i …f n ), where f i is the risk warning value of the ith monitoring sub-area at the current feedback time node.

[0013] In some embodiments of the present application, when generating the risk warning value f of the sub-area to be diagnosed at the current monitoring time node, it includes: f=e3*Q3*[ Y(i)*β i *(d i -r i *d' i )]+e4*Q4*U+e5*Q5*[ T(i)*β i *(d i -k i *d' i )]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; e5 is the preset fifth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; Q5 is the preset fifth fixed coefficient; θ3 is the number of risk characteristic indicators; β i is the influencing factor of the ith risk characteristic indicator; d i is the reference value of the risk characteristic index of the i-th sub-region to be diagnosed generated based on the characteristic data package; d' i is the evaluation value threshold of the ith risk characteristic indicator; r i is the correction coefficient of the i-th risk characteristic index set based on the first-level correction strategy of the sub-area to be diagnosed; Y(i) is the selection coefficient; if (d i -r i *d' i )>0,Y(i)=1; if (d i -r i *d' i )<0,Y(i)=0; T(i) is the selection coefficient; if (d i -k i *d' i )>0, T(i)=1; if (d i -k i *d' i )<0, T(i)=0; U is the historical risk value.

[0014] In some embodiments of the present application, when generating a primary correction strategy for the sub-region to be diagnosed, it includes: Obtain the environmental data packet of the sub-area to be diagnosed at the current monitoring time node; Set b successively according to the disturbance scenario sequence B i as the target disturbance scenario; Generate the similarity evaluation value g between the sub-region to be diagnosed and the target disturbance scenario according to the environmental data packet; Generate the similarity evaluation values between the sub-region to be diagnosed and each disturbance scenario successively; Establish a similarity evaluation value sequence G, G = (g1, g2... g i ... g m ), where g i is the similarity evaluation value between the sub-region to be diagnosed and the i-th disturbance scenario; Set the correction sub-strategy of the disturbance scenario corresponding to the maximum value g max in the similarity evaluation value sequence G as the primary correction strategy for the sub-region to be diagnosed.

[0015] In some embodiments of the present application, when generating the similarity evaluation value g between the sub-region to be diagnosed and the target disturbance scenario, it includes: g = Q6 * v i *(j i - j' i ) 2 ; where Q6 is a preset conversion coefficient; θ4 is the number of disturbance evaluation indicators; v i is the influence factor of the i-th disturbance evaluation indicator; j i is the reference value of the i-th disturbance evaluation indicator generated based on the environmental data packet; j' i is the reference value of the i-th disturbance evaluation indicator in the target disturbance scenario.

[0016] In some embodiments of the present application, judging whether to generate a warning instruction according to all risk warning values includes: Preset the first risk warning value threshold F1 and the second risk warning value threshold F2, and F1 < F2; If f i < F1, no warning instruction is generated for the i-th monitoring sub-region at the current monitoring time node; If F1 ≤ f i < F2, a primary warning instruction is generated for the i-th monitoring sub-region at the current monitoring time node; If f i ≥ F2, a secondary warning instruction is generated for the i-th monitoring sub-region at the current monitoring time node.

[0017] Compared with the prior art, the beneficial effect of a risk warning method for an above-ground pipe gallery based on multi-dimensional data fusion in an embodiment of the present application is that: The multi-dimensional data such as daily inspection risk data of the port's ground pipeline corridor, operation monitoring data collected by sensors, and historical construction data of the pipeline corridor are integrated and processed to cover multi-dimensional correlation factors related to risks, so as to provide timely warnings for potential risks of the port's ground pipeline corridor and ensure the safe operation of the port's ground pipeline corridor.

[0018] By analyzing environmental meteorological factors, constructing multiple disturbance scenarios, and dynamically adjusting the risk warning strategies under each disturbance scenario, we can accurately predict the probability and severity of various risks under specific meteorological conditions, avoid disturbances to the risk diagnosis model caused by environmental factors, and improve the risk warning accuracy and maintenance efficiency of the port's ground pipeline corridor. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a method for early warning of ground pipeline corridor risks based on multi-dimensional data fusion in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0020] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0021] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0022] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0023] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0024] like Figure 1 As shown, a method for early warning of ground pipe gallery risks based on multi-dimensional data fusion in a preferred embodiment of the present application includes: S101: Establish multiple monitoring sub-areas according to the equipment parameters of the pipe gallery, and set inspection strategies according to all monitoring sub-areas; S102: Acquire monitoring data packets and inspection data packets of each monitoring sub-area according to a preset monitoring time node; S103: Generate risk warning values ​​for each monitoring sub-area according to a preset risk diagnosis model, and determine whether to generate a warning instruction according to all risk warning values; When multiple monitoring sub-areas are set, they include: Establish a monitoring sub-area sequence A, A=(a1, a2…a i …a n ), where a i is the ith monitoring sub-area; n is the number of monitoring sub-areas.

[0025] Specifically, multiple monitoring sub-areas are established according to the different parameters of the above-ground pipeline corridor equipment in the port area.

[0026] Specifically, by setting up multiple monitoring points in the above-ground pipeline corridor in each monitoring sub-area and setting corresponding data acquisition equipment (including but not limited to various sensors, video monitoring equipment, etc.), various operating parameters of the above-ground pipeline corridor are collected and corresponding monitoring data packets are generated.

[0027] Specifically, manual inspections and drone equipment inspections are used to regularly obtain daily inspection risk data of the above-ground pipeline corridors in each monitoring sub-area and generate corresponding inspection data packets.

[0028] Specifically, when presetting the risk diagnosis model, it includes: Establish a fusion sub-model and set multiple risk characteristic indicators; Establish a diagnostic sub-model based on all risk characteristic indicators; Generate multiple disturbance evaluation indicators based on the historical environmental data of the pipeline corridor, and generate multiple disturbance scenarios based on all disturbance indicators; Establish a disturbance scenario sequence B, B=(b1, b2…b i …b m ), where b i is the ith disturbance scenario; m is the number of disturbance scenarios; Generate correction sub-strategies for each disturbance scenario, and establish a correction sub-model based on all correction sub-strategies; A risk diagnosis model is established based on the fusion sub-model, the diagnosis sub-model and the correction sub-model.

[0029] Specifically, the historical inspection risk data and historical monitoring data are collected, and the data are labeled with their corresponding risk categories. Then the data is preprocessed, including image normalization, data enhancement, and data set partitioning, so as to generate the corresponding training data packet and generate a diagnostic sub-model based on the training data.

[0030] Specifically, risk characteristic indicators include but are not limited to abnormal temperature in the corridor, structural stability, human error and human damage, pipe corrosion, abnormal vibration, settlement and other parameters.

[0031] Specifically, the fusion sub-model can fuse various types of data in the monitoring data packet and the inspection data packet according to the time dimension to form a new multi-dimensional data set.

[0032] Specifically, disturbance evaluation indicators include, but are not limited to, the historical operating time of the pipeline corridor, wind speed, ambient temperature, port geology, climate, hydrology and other parameters.

[0033] Specifically, multiple disturbance scenarios are generated according to the random combination of different value ranges of various disturbance indicators, and the corresponding training data packets are generated by collecting the historical risk data corresponding to each disturbance scenario, and the correction sub-strategies of each disturbance scenario are generated according to the training data packets.

[0034] Specifically, the correction sub-strategy refers to a dynamic adjustment strategy for the safety thresholds of various risk characteristic indicators in the current disturbance scenario, avoiding the interference of a single evaluation system on the accuracy of risk warning, thereby solving the problem that the traditional risk assessment model is based on static data or fixed thresholds to judge risks and has warning delays.

[0035] It can be understood that in the above-mentioned embodiment, multi-dimensional data such as daily inspection risk data of the port's ground pipeline corridor, operation monitoring data collected by sensors, and historical construction data of the pipeline corridor are integrated and processed to cover multi-dimensional correlation factors related to risks, so as to timely warn of potential risks of the port's ground pipeline corridor and ensure the safe operation of the port's ground pipeline corridor.

[0036] In a preferred embodiment of the present application, when multiple monitoring sub-areas are set, the following is also included: According to the monitoring sub-area sequence A, set a i Monitor sub-areas for the target; Obtain historical construction data and equipment data of the target monitoring sub-area to set the potential risk value c of the target monitoring sub-area; Set the potential risk value of each target monitoring sub-area in turn; Establish a potential risk value series C, C=(c1,c2…c i …c n ), where c iis the potential risk value of the ith monitoring sub-area; n is the number of monitoring sub-areas; According to the potential risk value sequence C, the compensation coefficient of each monitoring sub-area is set; Establish compensation coefficient sequence K, K=(k1,k2…k i …k n ), where k i is the compensation coefficient of the ith monitoring sub-area; n is the number of monitoring sub-areas.

[0037] Specifically, historical construction data refers to the record data of the building materials and construction process used in the construction of the above-ground pipeline corridor in each monitoring sub-area. By analyzing the historical construction data of each monitoring sub-area, the potential risk value of each monitoring sub-area is generated.

[0038] Specifically, the larger the potential risk value, the lower the structural stability of the above-ground pipeline corridor in the current monitoring sub-area due to construction quality, and the greater the possibility of operational risks.

[0039] Specifically, when setting the compensation coefficient for each monitoring sub-area, it includes: The first potential risk value interval (C1, C2), the second potential risk value threshold (C2, C3) and the third potential risk value threshold (C3, C4) are preset, and C1 <C2<C3<C4; If c i When in the preset first potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K1; If c i When in the preset second potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K2; If c i When in the preset third potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K3; and K3 <K2<K1<1。

[0040] Specifically, the larger the potential risk value, the smaller the corresponding correction coefficient, that is, the larger the potential risk value, the lower the corresponding safety threshold of each risk characteristic indicator. The safety threshold of each risk characteristic indicator in a single monitoring sub-area is dynamically adjusted through the correction coefficient, and the influence of each pipeline corridor's own parameters on the operation risk is fully considered, thereby improving the early warning accuracy of the pipeline corridor operation risk in each monitoring sub-area.

[0041] Specifically, when setting the potential risk value c of the target monitoring sub-area, it includes: c=e1*Q1*[ η 1i *si ]+e2*Q2*[ η2i *w i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ1 is the number of construction risk indicators; η 1i is the influencing factor of the i-th construction risk index; s i is the reference value of the i-th construction risk index of the target monitoring sub-area; θ2 is the number of equipment evaluation indicators; η 2i is the influencing factor of the i-th equipment evaluation index; w i is the reference value of the evaluation index of the i-th device in the target monitoring sub-area.

[0042] Specifically, all parameters in the model are normalized by presetting the first fixed coefficient and the second fixed coefficient, so that each parameter in each model is within the same value range.

[0043] Specifically, construction risk indicators include but are not limited to the number of violations during the construction process, the quality of materials during the construction process, the degree of environmental interference during the construction process, and other parameters. By quantifying each construction evaluation indicator, the more favorable it is to the stability of the corridor, the smaller the corresponding reference value. Equipment evaluation indicators include but are not limited to corridor volume, equipment category and equipment level inside the corridor, and other parameters. By quantifying each equipment evaluation indicator, the greater the loss caused by the occurrence of operating risks, the greater the value of the corresponding equipment evaluation indicator.

[0044] It can be understood that in the above embodiment, the historical construction data of each monitoring sub-area is analyzed to generate the potential risk value of each monitoring sub-area, and the safety threshold of each risk characteristic indicator of the monitoring sub-area is dynamically adjusted by setting the correction coefficient, so as to fully consider the influence of the own parameters of each pipeline corridor on the operation risk, thereby improving the early warning accuracy of the operation risk of the pipeline corridor in each monitoring sub-area.

[0045] In a preferred embodiment of the present application, when generating the risk warning value of each monitoring sub-area, it includes: According to the monitoring sub-area sequence A, set a i is the sub-region to be diagnosed; Obtain monitoring data packets and inspection data packets of the sub-area to be diagnosed at the current monitoring time node; Generate a feature data packet of the sub-area to be diagnosed at the current monitoring time node according to the preprocessing result of the monitoring data packet and the inspection data packet by the fusion sub-model; Generate a risk warning value f of the sub-area to be diagnosed at the current monitoring time node according to the diagnosis sub-model and the feature data packet; Generate the risk warning value of each monitoring sub-area at the current monitoring time node in sequence; Establish a risk warning value series F, F=(f1, f2…f i …f n ), where f i is the risk warning value of the ith monitoring sub-area at the current feedback time node.

[0046] Specifically, the fusion sub-model fuses various types of data in the monitoring data package and the inspection data package according to the time dimension to form a feature data package, which includes the reference values ​​of various risk characteristic indicators.

[0047] Specifically, the larger the risk warning value, the greater the possibility that there is an operational risk in the pipeline corridor in the corresponding monitoring sub-area.

[0048] Specifically, when generating the risk warning value f of the sub-area to be diagnosed at the current monitoring time node, it includes: f=e3*Q3*[ Y(i)*β i *(d i -r i *d' i )]+e4*Q4*U+e5*Q5*[ T(i)*β i *(d i -k i *d' i )]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; e5 is the preset fifth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; Q5 is the preset fifth fixed coefficient; θ3 is the number of risk characteristic indicators; β i is the influencing factor of the ith risk characteristic indicator; d i is the reference value of the risk characteristic index of the i-th sub-region to be diagnosed generated based on the characteristic data package; d' i is the evaluation value threshold of the ith risk characteristic indicator; r i is the correction coefficient of the i-th risk characteristic index set based on the first-level correction strategy of the sub-area to be diagnosed; Y(i) is the selection coefficient; if (d i -r i *d' i )>0,Y(i)=1; if (d i -r i *d' i) < 0, Y(i) = 0; T(i) is the selection coefficient; if (d i -k i *d' i ) > 0, T(i) = 1; if (d i -k i *d' i ) < 0, T(i) = 0; U is the historical risk value.

[0049] Specifically, by presetting the third fixed coefficient, the fourth fixed coefficient, and the fifth fixed coefficient, all parameters in the model are normalized, so that each parameter in the model is within the same value range.

[0050] Specifically, the historical risk value is set according to the change trend of the risk warning value at the historical monitoring time node. The greater the historical risk value, the greater the degree of cumulative increase in the risk probability.

[0051] Specifically, it is determined whether to generate a warning instruction according to all risk warning values, including: Preset the first risk warning value threshold F1 and the second risk warning value threshold F2, and F1 < F2; If f i < F1, no warning instruction is generated for the i-th monitoring sub-region at the current monitoring time node; If F1 ≤ f i < F2, a first-level warning instruction is generated for the i-th monitoring sub-region at the current monitoring time node; If f i ≥ F2, a second-level warning instruction is generated for the i-th monitoring sub-region at the current monitoring time node.

[0052] Specifically, the first-level warning instruction means that there are potential operation risks or real-time operation risks in the pipe gallery within the current monitoring sub-region, and the category and impact degree are small, which do not affect the normal operation of the pipe gallery. The judgment results of the remaining monitoring sub-regions can be combined to conduct joint maintenance on multiple monitoring sub-regions within the limited time limit, improve the overall maintenance efficiency, and reduce the overall maintenance cost. The second-level warning instruction means that there are serious operation risks in the pipe gallery within the current monitoring sub-region, and immediate maintenance is required to avoid further losses.

[0053] In the preferred embodiment of this application, when generating the first-level correction strategy for the sub-region to be diagnosed, it includes: Obtain the environmental data packet of the sub-region to be diagnosed at the current monitoring time node; According to the disturbance scenario sequence B, set b i as the target disturbance scenario; Generate the similarity evaluation value g between the sub-region to be diagnosed and the target disturbance scenario according to the environmental data packet; Generate similarity evaluation values ​​between the sub-area to be diagnosed and each disturbance scenario in sequence; Establish a similar evaluation value sequence G, G = (g1, g2…g i …g m ), where g i is the similarity evaluation value between the sub-area to be diagnosed and the i-th disturbance scene; Set the maximum value g in the similarity evaluation value sequence G max The correction sub-strategy of the corresponding disturbance scenario is the first-level correction strategy of the sub-area to be diagnosed.

[0054] Specifically, by analyzing the real-time environmental data of the sub-area to be diagnosed, the correction strategy corresponding to the best disturbance sub-scenario is selected, and the safety thresholds of various risk characteristic indicators in real time are corrected to improve the risk warning accuracy of the sub-area to be diagnosed.

[0055] Specifically, when generating the similarity evaluation value g between the sub-area to be diagnosed and the target disturbance scene, it includes: g=Q6*[ v i *(j i -j' i ) 2 ]; Among them, Q6 is the preset conversion coefficient; θ4 is the number of disturbance evaluation indicators; v i is the influencing factor of the i-th disturbance evaluation index; j i is the reference value of the i-th disturbance evaluation index generated based on the environmental data packet; j' i is the reference value of the i-th disturbance evaluation index in the target disturbance scenario.

[0056] Specifically, the larger the similarity evaluation is, the more similar the current environmental parameters of the sub-area to be diagnosed are to the corresponding disturbance scenario.

[0057] Specifically, by comparing the real-time environmental parameters in the sub-area to be diagnosed with each disturbance scenario, the corresponding disturbance scenario is quickly selected to correct the safety threshold of each risk characteristic indicator.

[0058] Specifically, by establishing multiple disturbance scenarios, the dynamic characteristics of the formation and development of pipeline corridor risks are fully simulated. For example, under continuous high temperature weather conditions, port equipment may deform its components due to thermal expansion and contraction, resulting in an increased risk of equipment failure. This solves the problem that static risk assessment models are difficult to capture the gradual accumulation of these risks over time and environmental changes, which in turn causes port management to miss the best time to take effective countermeasures.

[0059] According to the first concept of the present application, multi-dimensional data such as daily inspection risk data of the port's ground pipeline corridor, operation monitoring data collected by sensors, and historical construction data of the pipeline corridor are integrated and processed to cover multi-dimensional correlation factors related to risks, so as to provide timely warnings of potential risks of the port's ground pipeline corridor and ensure the safe operation of the port's ground pipeline corridor.

[0060] According to the second concept of the present application, by analyzing the environmental meteorological factors, constructing multiple disturbance scenarios, and dynamically adjusting the risk warning strategies under each disturbance scenario, the probability and severity of various risks under specific meteorological conditions can be accurately predicted, thereby avoiding disturbances to the risk diagnosis model due to environmental factors and improving the risk warning accuracy and maintenance efficiency of the port's ground pipeline corridor.

[0061] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A risk warning method for above-ground pipe gallery based on multi-dimensional data fusion, characterized in that: include: Establish multiple monitoring sub-areas based on the equipment parameters of the tunnel, and set inspection strategies based on all monitoring sub-areas; Acquire monitoring data packets and inspection data packets of each monitoring sub-area according to the preset monitoring time node; Generate risk warning values ​​for each monitoring sub-area based on the preset risk diagnosis model, and determine whether to generate warning instructions based on all risk warning values; When multiple monitoring sub-areas are set, they include: Establish a monitoring sub-area sequence A, A=(a1, a2…a i …a n ), where a i is the ith monitoring sub-area; n is the number of monitoring sub-areas.

2. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion according to claim 1 is characterized in that: When presetting the risk diagnosis model, it includes: Establish a fusion sub-model and set multiple risk characteristic indicators; Establish a diagnostic sub-model based on all risk characteristic indicators; Generate multiple disturbance evaluation indicators based on the historical environmental data of the pipeline corridor, and generate multiple disturbance scenarios based on all disturbance indicators; Establish a disturbance scenario sequence B, B=(b1, b2…b i …b m ), where b i is the ith disturbance scenario; m is the number of disturbance scenarios; Generate correction sub-strategies for each disturbance scenario, and establish a correction sub-model based on all correction sub-strategies; A risk diagnosis model is established based on the fusion sub-model, the diagnosis sub-model and the correction sub-model.

3. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 2 is characterized in that: When setting multiple monitoring sub-areas, it also includes: According to the monitoring sub-area sequence A, set a i Monitor sub-areas for the target; Obtain historical construction data and equipment data of the target monitoring sub-area to set the potential risk value c of the target monitoring sub-area; Set the potential risk value of each target monitoring sub-area in turn; Establish a potential risk value series C, C=(c1,c2…c i …c n ), where c i is the potential risk value of the ith monitoring sub-area; n is the number of monitoring sub-areas; According to the potential risk value sequence C, the compensation coefficient of each monitoring sub-area is set; Establish compensation coefficient sequence K, K=(k1,k2…k i …k n ), where k i is the compensation coefficient of the ith monitoring sub-area; n is the number of monitoring sub-areas.

4. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 3 is characterized in that: When setting the compensation coefficient for each monitoring sub-area, include: The first potential risk value interval (C1, C2), the second potential risk value threshold (C2, C3) and the third potential risk value threshold (C3, C4) are preset, and C1 <C2<C3<C4; If c i When in the preset first potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K1; If c i When in the preset second potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K2; If c i When in the preset third potential risk interval, set the compensation coefficient k of the i-th monitoring sub-area i =K3; and K3 <K2<K1<1。 5. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 3 is characterized in that: When setting the potential risk value c of the target monitoring sub-area, it includes: c=e1*Q1*[ η 1i *s i ]+e2*Q2*[ η2i *w i ]; Wherein, e1 is the preset first weight coefficient; e2 is the preset second weight coefficient; Q1 is the preset first fixed coefficient; Q2 is the preset second fixed coefficient; θ1 is the number of construction risk indicators; η 1i is the influencing factor of the i-th construction risk index; s i is the reference value of the i-th construction risk index of the target monitoring sub-area; θ2 is the number of equipment evaluation indicators; η 2i is the influencing factor of the i-th equipment evaluation index; w i is the reference value of the evaluation index of the ith device in the target monitoring sub-area.

6. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 5 is characterized in that: When generating risk warning values ​​for each monitoring sub-area, it includes: According to the monitoring sub-area sequence A, set a i is the sub-region to be diagnosed; Obtain monitoring data packets and inspection data packets of the sub-area to be diagnosed at the current monitoring time node; Generate a feature data packet of the sub-area to be diagnosed at the current monitoring time node according to the preprocessing result of the monitoring data packet and the inspection data packet by the fusion sub-model; Generate a risk warning value f of the sub-area to be diagnosed at the current monitoring time node according to the diagnosis sub-model and the feature data packet; Generate the risk warning value of each monitoring sub-area at the current monitoring time node in sequence; Establish a risk warning value series F, F=(f1, f2…f i …f n ), where f i is the risk warning value of the ith monitoring sub-area at the current feedback time node.

7. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 6 is characterized in that: When generating the risk warning value f of the sub-area to be diagnosed at the current monitoring time node, it includes: f=e3*Q3*[ Y(i)*β i *(d i -r i *d' i )]+e4*Q4*U+e5*Q5*[ T(i)*β i *(d i -k i *d' i )]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; e5 is the preset fifth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; Q5 is the preset fifth fixed coefficient; θ3 is the number of risk characteristic indicators; β i is the influencing factor of the ith risk characteristic indicator; d i is the reference value of the risk characteristic index of the i-th sub-region to be diagnosed generated based on the characteristic data package; d' i is the evaluation value threshold of the ith risk characteristic indicator; r i is the correction coefficient of the i-th risk characteristic index set based on the first-level correction strategy of the sub-area to be diagnosed; Y(i) is the selection coefficient; if (d i -r i *d' i )>0,Y(i)=1; if (d i -r i *d' i )<0,Y(i)=0; T(i) is the selection coefficient; if (d i -k i *d' i )>0, T(i)=1; if (d i -k i *d' i )<0, T(i)=0; U is the historical risk value.

8. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 7 is characterized in that: When generating the first-level correction strategy for the sub-area to be diagnosed, it includes: Obtain the environmental data packet of the sub-area to be diagnosed at the current monitoring time node; Set b in sequence according to the disturbance scenario sequence B i Perturb the scene for the target; Generate a similarity evaluation value g between the sub-area to be diagnosed and the target disturbance scene according to the environmental data packet; Generate similarity evaluation values ​​between the sub-area to be diagnosed and each disturbance scenario in sequence; Establish a similar evaluation value sequence G, G = (g1, g2…g i …g m ), where g i is the similarity evaluation value between the sub-area to be diagnosed and the i-th disturbance scene; Set the maximum value g in the similarity evaluation value sequence G max The correction sub-strategy of the corresponding disturbance scenario is the first-level correction strategy of the sub-area to be diagnosed.

9. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion as claimed in claim 8, characterized in that: When generating the similarity evaluation value g between the sub-area to be diagnosed and the target disturbance scene, it includes: g=Q6*[ in i *(j i -j' i ) 2 ]; Among them, Q6 is the preset conversion coefficient; θ4 is the number of disturbance evaluation indicators; v i is the influencing factor of the i-th disturbance evaluation index; j i is the reference value of the i-th disturbance evaluation index generated based on the environmental data packet; j' i is the reference value of the i-th disturbance evaluation index in the target disturbance scenario.

10. The above-ground utility corridor risk early warning method based on multi-dimensional data fusion according to claim 9, characterized in that: Determine whether to generate a warning instruction based on all risk warning values, including: A first risk warning value threshold F1 and a second risk warning value threshold F2 are preset, and F1 <F2; If f i <F1, the i-th monitoring sub-region does not generate a warning instruction at the current monitoring time node; If F1 ≤ f i <F2, the i-th monitoring sub-region generates a first-level early warning instruction at the current monitoring time node; If f i ≥F2, the i-th monitoring sub-area generates a secondary warning instruction at the current monitoring time node.

Images