Wharf accessory intelligent management method and system based on big data analysis

Abstract

The invention relates to the technical field of wharf accessories, in particular to a wharf accessory intelligent management method and system based on big data analysis. Comprising the following steps: setting a plurality of sub-devices according to accessory parameters, and constructing a state monitoring model and an operation scheduling model based on all the sub-devices; setting a plurality of scheduling sub-strategies according to the to-be-processed cargo parameters and the operation scheduling model, and generating an equipment control strategy according to the state monitoring model and all the scheduling sub-strategies; generating an operation risk value of each sub-device according to a preset diagnosis time node, and judging whether an early warning instruction is generated or not according to all the operation risk values; a cargo identification sub-model is constructed based on big data analysis, characteristic parameters of to-be-processed cargoes are identified in time, a plurality of scheduling strategies are selected according to the characteristic parameters, real-time operation states of all accessories are obtained according to a state monitoring model, and all the scheduling strategies are optimized, so that the overall scheduling operation efficiency of the accessories is improved, and the scheduling efficiency of the to-be-processed cargoes is improved. The loading and unloading efficiency and the equipment operation efficiency are improved.

Description

Technical Field

[0001] The present application relates to the technical field of dock tool accessories, and in particular to an intelligent management method and system for dock tool accessories based on big data analysis. Background Art

[0002] The management of tools and equipment at traditional general cargo terminals relies on manual experience and has the following problems: 1. The scheduling efficiency of tools and equipment (such as spreaders, forklifts, and shelves) is low, and equipment is easily idle or overloaded due to task conflicts; 2. Equipment failure prediction is delayed and maintenance costs are high; 3. The cargo loading plan lacks real-time dynamic optimization, which affects loading and unloading efficiency; 4. The utilization rate of historical data is low. Although there are some automated management systems in the existing technology, they lack the dynamic decision-making capabilities of multi-source data fusion. Summary of the invention

[0003] The purpose of this application is: to solve the above-mentioned technical problems, this application provides a method and system for intelligent management of dock tools and accessories based on big data analysis, aiming to improve the scheduling and management efficiency of dock tools and accessories, and realize intelligent scheduling, status monitoring and performance optimization of tools and accessories.

[0004] In some embodiments of the present application, a cargo identification sub-model is constructed based on big data analysis to timely identify characteristic parameters of the cargo to be processed, multiple scheduling strategies are selected based on the characteristic parameters, and the real-time operating status of each tool is obtained based on the status monitoring model to optimize each scheduling strategy, thereby improving the overall scheduling and operation efficiency of the tools, and improving the loading and unloading efficiency and equipment operation efficiency.

[0005] In some embodiments of the present application, by establishing a mapping sub-model for each tool, remote monitoring and fault diagnosis of the operating status of each tool can be achieved, and timely warnings of potential failure risks of each tool can be given, thereby reducing the overall operation and maintenance costs. At the same time, by monitoring the status of each tool, the cargo loading plan can be dynamically optimized in real time, thereby improving the loading and unloading efficiency of cargo.

[0006] In some embodiments of the present application, a method for intelligent management of dock tooling based on big data analysis is provided, including: Set multiple sub-equipment according to tool parameters, and build a condition monitoring model and operation scheduling model based on all sub-equipment; Set multiple scheduling sub-strategies according to the parameters of the cargo to be processed and the operation scheduling model, and generate equipment control strategies according to the status monitoring model and all scheduling sub-strategies; Generate the operation risk value of each sub-device according to the preset diagnosis time node, and determine whether to generate an early warning instruction based on all the operation risk values; When setting multiple sub-devices, it includes: Create a sub-device array A, A=(a1,a2…a i …a n ), where a i is the i-th sub-device; n is the number of sub-devices.

[0007] In some embodiments of the present application, when constructing a state monitoring model and an operation scheduling model, it includes: Set a in sequence according to the sub-device sequence A i is the target sub-device; Construct a mapping sub-model for the target sub-device and set a monitoring sub-strategy for the target sub-device; Set multiple feedback time nodes of the target sub-device according to the monitoring sub-strategy; Obtaining a feedback data packet from the target sub-device according to a preset feedback time node; Update the mapping sub-model of the target sub-device according to the feedback data packet; Set the mapping sub-model and monitoring sub-strategy of each sub-device in turn; Construct a state monitoring model based on all mapping sub-models and all monitoring sub-strategies; Generate multiple cargo characteristic indicators based on historical cargo parameters; Construct a cargo identification sub-model based on all cargo characteristic indicators; Generate multiple first-level scheduling strategies based on the historical scheduling parameters of tools and accessories; Build a strategy database based on all first-level scheduling strategies; The operation scheduling model is constructed based on the cargo identification sub-model and the strategy database.

[0008] In some embodiments of the present application, when multiple scheduling sub-strategies are set according to the parameters of the goods to be processed and the operation scheduling model, it includes: The cargo identification sub-model pre-processes the cargo parameters to be processed and generates a cargo feature data packet according to the pre-processing results; Set up screening sub-strategies based on cargo feature data packages; Filtering in the policy database based on the screening sub-policy, and generating multiple scheduling sub-policies according to the screening results; Establish a scheduling sub-strategy sequence B, B=(b1, b2…b i …b m ), where b i is the i-th scheduling sub-strategy; m is the number of scheduling sub-strategies.

[0009] In some embodiments of the present application, when generating a device control strategy based on a state monitoring model and all scheduling sub-strategies, it includes: According to the scheduling sub-strategy sequence B, set bi as the target scheduling sub-strategy in sequence; Generate a scheduling evaluation value c of the target scheduling sub-strategy based on the state monitoring model; c=e1*Q1*[ (β 1i *p i )]+e2*Q2*[ (β 2i *j i )]; Among them, 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 strategy evaluation indicators; β 1i is the influencing factor of the i-th strategy evaluation index set based on the cargo feature data package; p i is the reference value of the i-th strategy evaluation index generated based on the target scheduling sub-strategy; θ2 is the number of operating indicators; β 2i is the influencing factor of the i-th operating indicator; j i is the reference value of the i-th operation evaluation index in the target scheduling sub-strategy generated based on the condition monitoring model; Generate scheduling evaluation values ​​of each scheduling sub-strategy in turn; Establish the scheduling evaluation value sequence C, C=(c1, c2…c i …c m ), where c i is the scheduling evaluation value of the i-th scheduling sub-strategy; Set the maximum value c in the scheduling evaluation value sequence C max The corresponding scheduling sub-strategy is a first-level sub-strategy; Generate equipment control strategy based on the first-level sub-strategy and condition monitoring model; Determine whether to generate a correction instruction for the equipment control strategy according to a preset monitoring time node; When the device control strategy is executed, a record data packet is generated; Determine whether to update the policy database based on the recorded data packets.

[0010] In some embodiments of the present application, determining whether to generate a correction instruction for a device control strategy includes: Get the monitoring data packet of the current monitoring time node; Generate a deviation evaluation value f of the device control strategy according to the monitoring data packet; f=[ η i *v i ]; Among them, θ3 is the number of deviation evaluation indicators; η i is the influencing factor of the i-th deviation evaluation index; v i is the reference value of the i-th deviation evaluation index generated based on the monitoring data packet; Preset deviation evaluation value threshold F1; If f>F1, the current monitoring time node generates a first-level correction instruction for the equipment control strategy.

[0011] In some embodiments of the present application, when generating the operation risk value of each sub-device according to the preset diagnosis time node, it includes: Preset multiple evaluation cycles, and set the end time node of each evaluation cycle as the diagnosis time node; Set a in sequence according to the sub-device sequence A i is the sub-device to be evaluated; Establish multiple time intervals within the current evaluation cycle according to the monitoring sub-strategy of the sub-device to be evaluated; Generate abnormal evaluation values ​​in each time interval; Establish the abnormal evaluation value sequence G of the sub-equipment to be evaluated, G=(g1,g2…g i …g r ), where g i is the abnormal evaluation value of the i-th sub-device to be evaluated in the i-th time interval; r is the number of time intervals; Generate the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node according to the abnormal evaluation value sequence G; Generate the operation risk value of each sub-equipment in turn; Establish the diagnostic risk value series H at the current diagnostic time node, H = (h1, h2…h i … hn ), where h i is the operating risk value of the i-th sub-device at the current diagnosis time node.

[0012] In some embodiments of the present application, when generating the operation risk value h of the sub-device to be evaluated at the current diagnosis time node, it includes: h=e3*Q3*[ α 1i *k i ]+e4*Q4*[ α 2i *w i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; s1 is the number of abnormal evaluation indicators; α 1i is the influencing factor of the i-th abnormal evaluation index; k i is the reference value of the i-th abnormal evaluation index generated based on the abnormal evaluation value sequence G; s2 is the number of equipment risk indicators; α 2i is the influencing factor of the i-th equipment risk index; w iis the reference value of the i-th equipment risk index generated based on the sub-equipment to be evaluated.

[0013] In some embodiments of the present application, a dock tool intelligent management system based on big data analysis is provided, including: The central control platform is used to set multiple sub-equipment according to tool parameters and build a status monitoring model and operation scheduling model based on all sub-equipment; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are arranged on each sub-device; The monitoring unit is used to collect the operation data of each sub-device and generate a feedback data packet of each sub-device; A collection unit, used to obtain parameters of the goods to be processed; The central control platform includes: The first processing module is used to establish a sub-device sequence A, A=(a1, a2…a i …a n ), where a i is the ith sub-device; n is the number of sub-devices; The second processing module is used to build a condition monitoring model and an operation scheduling model; The third processing module is used to set multiple scheduling sub-strategies according to the parameters of the goods to be processed and the operation scheduling model; The third processing module is also used to generate a device control strategy based on the state monitoring model and all scheduling sub-strategies; The early warning module is used to generate the operation risk value of each sub-device according to the preset diagnosis time node, and determine whether to generate an early warning instruction based on all the operation risk values.

[0014] In some embodiments of the present application, the third processing module is further used to: Obtain the preprocessing result of the cargo identification sub-model on the parameters of the cargo to be processed; Generate cargo feature data package according to preprocessing results; Set up screening sub-strategies based on cargo feature data packages; Filtering in the policy database based on the screening sub-policy, and generating multiple scheduling sub-policies according to the screening results; Establish a scheduling sub-strategy sequence B, B=(b1, b2…b i …b m ), where b i is the i-th scheduling sub-strategy; m is the number of scheduling sub-strategies; Generate scheduling evaluation values ​​of each scheduling sub-strategy in turn; Establish the scheduling evaluation value sequence C, C=(c1, c2…c i …c m ), where c iis the scheduling evaluation value of the i-th scheduling sub-strategy; Set the maximum value c in the scheduling evaluation value sequence C max The corresponding scheduling sub-strategy is a first-level sub-strategy; Generate equipment control strategy based on the first-level sub-strategy and condition monitoring model; Determine whether to generate a correction instruction for the equipment control strategy according to a preset monitoring time node; When the device control strategy is executed, a record data packet is generated; Determine whether to update the policy database based on the recorded data packets.

[0015] In some embodiments of the present application, the early warning module is also used to: Preset multiple evaluation cycles, and set the end time node of each evaluation cycle as the diagnosis time node; Set a in sequence according to the sub-device sequence A i is the sub-device to be evaluated; Establish multiple time intervals within the current evaluation cycle according to the monitoring sub-strategy of the sub-device to be evaluated; Generate abnormal evaluation values ​​in each time interval; Establish the abnormal evaluation value sequence G of the sub-equipment to be evaluated, G=(g1,g2…g i …g r ), where g i is the abnormal evaluation value of the i-th sub-device to be evaluated in the i-th time interval; r is the number of time intervals; Generate the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node according to the abnormal evaluation value sequence G; h=e3*Q3*[ α 1i *k i ]+e4*Q4*[ α 2i *w i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; s1 is the number of abnormal evaluation indicators; α 1i is the influencing factor of the i-th abnormal evaluation index; k i is the reference value of the i-th abnormal evaluation index generated based on the abnormal evaluation value sequence G; s2 is the number of equipment risk indicators; α 2i is the influencing factor of the i-th equipment risk index; w i is the reference value of the i-th equipment risk index generated based on the sub-equipment to be evaluated; Generate the operation risk value of each sub-equipment in turn; Establish the diagnostic risk value series H at the current diagnostic time node, H = (h1, h2…h i … hn ), where h i is the operating risk value of the i-th sub-device at the current diagnosis time node.

[0016] Compared with the prior art, the intelligent management method and system of dock tool accessories based on big data analysis in the embodiment of the present application has the following beneficial effects: Based on big data analysis, a cargo identification sub-model is constructed to timely identify the characteristic parameters of the cargo to be processed, select multiple scheduling strategies based on the characteristic parameters, and optimize each scheduling strategy by obtaining the real-time operating status of each tool based on the status monitoring model, thereby improving the overall scheduling and operation efficiency of the tools, and improving the loading and unloading efficiency and equipment operation efficiency.

[0017] By establishing a mapping sub-model for each tool, remote monitoring and fault diagnosis of the operating status of each tool can be achieved, and timely warnings can be given for potential failure risks of each tool, reducing the overall operation and maintenance costs. At the same time, by monitoring the status of each tool, the cargo loading plan can be dynamically optimized in real time, thereby improving the loading and unloading efficiency of cargo. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of an intelligent management method for dock tool accessories based on big data analysis in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] like Figure 1 As shown, a method for intelligent management of dock tools based on big data analysis in a preferred embodiment of the present application includes: S101: multiple sub-equipment are set according to tool parameters, and a status monitoring model and an operation scheduling model are constructed based on all sub-equipment; S102: setting multiple scheduling sub-strategies according to the parameters of the goods to be processed and the operation scheduling model, and generating equipment control strategies according to the state monitoring model and all scheduling sub-strategies; S103: generating an operation risk value for each sub-device according to a preset diagnosis time node, and determining whether to generate an early warning instruction according to all the operation risk values; When setting multiple sub-devices, it includes: Create a sub-device array A, A=(a1,a2…a i …a n ), where a i is the i-th sub-device; n is the number of sub-devices.

[0024] Specifically, the cargo parameters to be processed include: loading and unloading work orders, image data of the cargo pile and other parameters.

[0025] Specifically, multiple sub-equipment are established based on all the tools and accessories of the terminal (such as spreaders, forklifts, shelves, etc.), where a single sub-equipment represents a tool and accessory. For example, a single forklift represents a sub-equipment, and a single spreader represents a sub-equipment.

[0026] Specifically, when building a condition monitoring model and an operation scheduling model, it includes: Set a in sequence according to the sub-device sequence A i is the target sub-device; Construct a mapping sub-model for the target sub-device and set a monitoring sub-strategy for the target sub-device; Set multiple feedback time nodes of the target sub-device according to the monitoring sub-strategy; Obtaining a feedback data packet from the target sub-device according to a preset feedback time node; Update the mapping sub-model of the target sub-device according to the feedback data packet; Set the mapping sub-model and monitoring sub-strategy of each sub-device in turn; Construct a state monitoring model based on all mapping sub-models and all monitoring sub-strategies; Generate multiple cargo characteristic indicators based on historical cargo parameters; Construct a cargo identification sub-model based on all cargo characteristic indicators; Generate multiple first-level scheduling strategies based on the historical scheduling parameters of tools and accessories; Build a strategy database based on all first-level scheduling strategies; The operation scheduling model is constructed based on the cargo identification sub-model and the strategy database.

[0027] Specifically, the historical operating parameters of the target sub-device are obtained, and a corresponding mapping sub-model is constructed based on the analysis of the historical operating parameters, and the mapping sub-model can simulate the operating status of the sub-device.

[0028] Specifically, by setting the monitoring sub-strategy of the target sub-device, various operating parameters of the target sub-device are periodically collected, the corresponding feedback data packet is generated, and the corresponding mapping sub-model is periodically updated according to the feedback data packet, thereby realizing remote monitoring of the operating status of the target sub-device.

[0029] Specifically, various operating parameters include but are not limited to the real-time location of the target sub-device, whether the target sub-device is in working condition, the operating temperature of the target sub-device, vibration frequency, working time, unmaintained time, accumulated wear, rest time, equipment environment data and other parameters. Comprehensive monitoring of the target sub-device is achieved by collecting multi-dimensional data.

[0030] Specifically, based on obtaining all historical cargo parameters, a multimodal large model is constructed based on big data analysis technology, and multiple data such as text (work orders) and images (cargo pile type recognition) are integrated for joint analysis to construct a cargo identification sub-model.

[0031] Specifically, multiple cargo characteristic indicators are generated based on historical cargo parameters. After quantifying each cargo characteristic indicator, multiple value intervals of each cargo characteristic indicator are generated. Multiple cargo categories are constructed based on random combinations of each value interval. By processing historical scheduling parameters, a first-level scheduling strategy for each cargo category is generated. The first-level scheduling strategy for a single cargo category can be one or more.

[0032] Specifically, the first-level scheduling strategy includes multiple parameters such as the required tool types and the quantity of each tool type.

[0033] Specifically, cargo characteristic indicators include but are not limited to cargo category, cargo quantity, cargo stack type, cargo unloading delay cost and other parameters.

[0034] In a preferred embodiment of the present application, when multiple scheduling sub-strategies are set according to the parameters of the goods to be processed and the operation scheduling model, the following are included: The cargo identification sub-model pre-processes the cargo parameters to be processed and generates a cargo feature data packet according to the pre-processing results; Set up screening sub-strategies based on cargo feature data packages; Filtering in the policy database based on the screening sub-policy, and generating multiple scheduling sub-policies according to the screening results; Establish a scheduling sub-strategy sequence B, B=(b1, b2…b i …b m ), where b i is the i-th scheduling sub-strategy; m is the number of scheduling sub-strategies.

[0035] Specifically, the screening sub-strategy refers to comparing the similarity of the cargo feature data package with each cargo category. If the similarity exceeds the preset threshold, the cargo to be processed is matched with the corresponding cargo category, and the first-level scheduling strategies corresponding to all matching cargo categories are selected to construct a scheduling sub-strategy series.

[0036] Specifically, when generating the equipment control strategy based on the condition monitoring model and all scheduling sub-strategies, it includes: According to the scheduling sub-strategy sequence B, set bi as the target scheduling sub-strategy in sequence; Generate a scheduling evaluation value c of the target scheduling sub-strategy based on the state monitoring model; c=e1*Q1*[ (β 1i *p i )]+e2*Q2*[ (β 2i *j i )]; Among them, 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 strategy evaluation indicators; β 1i is the influencing factor of the i-th strategy evaluation index set based on the cargo feature data package; p i is the reference value of the i-th strategy evaluation index generated based on the target scheduling sub-strategy; θ2 is the number of operating indicators; β 2i is the influencing factor of the i-th operating indicator; j i is the reference value of the i-th operation evaluation index in the target scheduling sub-strategy generated based on the condition monitoring model; Generate scheduling evaluation values ​​of each scheduling sub-strategy in turn; Establish the scheduling evaluation value sequence C, C=(c1, c2…c i …c m), where c i is the scheduling evaluation value of the i-th scheduling sub-strategy; Set the maximum value c in the scheduling evaluation value sequence C max The corresponding scheduling sub-strategy is a first-level sub-strategy; Generate equipment control strategy based on the first-level sub-strategy and condition monitoring model; Determine whether to generate a correction instruction for the equipment control strategy according to a preset monitoring time node; When the device control strategy is executed, a record data packet is generated; Determine whether to update the policy database based on the recorded data packets.

[0037] Specifically, the strategy evaluation indicators include, but are not limited to, scheduling cost, expected working time of each tool in the strategy, workload, expected wear, expected unloading time, etc. By quantifying each strategy evaluation indicator, each scheduling sub-strategy can be evaluated in multiple dimensions.

[0038] Specifically, by dynamically adjusting the influencing factors of each strategy evaluation index, multiple optimization directions can be achieved. For example, for goods with neat shapes and not easy to break, the optimization direction is the direction of short unloading cycle, and for goods with long unloading cycle, the optimization direction is the direction of low tool operation load. The mapping relationship between the optimization direction and each cargo characteristic index can be set according to the historical scheduling parameters.

[0039] Specifically, the optimal search direction of the goods to be processed can be set according to the goods feature data packet.

[0040] Specifically, the operating indicators include, but are not limited to, the ability of the remaining tools to cope with the sudden increase in unloading tasks after completing the current scheduling sub-strategy, the number of spare tools of the current scheduling sub-strategy, the probability of progress fluctuations during the execution of the current scheduling sub-strategy, and other parameters.

[0041] Specifically, the greater the dispatch evaluation value, the greater the comprehensive benefit of executing the current dispatch sub-strategy, the stronger the ability to cope with sudden unloading tasks, and the higher the overall operating efficiency.

[0042] Specifically, the types of tools and accessories that need to be called and the quantity of each type are obtained according to the first-level sub-strategy, and then the real-time status of all tools and accessories is traversed through the status monitoring model, and the most suitable tools and accessories are selected for scheduling to avoid equipment idleness or overload due to task conflicts and ensure the work efficiency of each tool and accessory.

[0043] Specifically, the current cargo loading and unloading plan is fully recorded, the corresponding record data package is generated, and the record data is placed in the strategy database. The corresponding first-level scheduling strategy is optimized through big data analysis, thereby realizing dynamic updating of the strategy database and ensuring the overall operation scheduling efficiency.

[0044] Specifically, all parameters in the model are normalized by presetting the first fixed coefficient and the second fixed coefficient, so that each parameter in the model is in the same value range.

[0045] Specifically, when determining whether to generate a correction instruction for the device control strategy, it includes: Get the monitoring data packet of the current monitoring time node; Generate a deviation evaluation value f of the device control strategy according to the monitoring data packet; f=[ η i *v i ]; Among them, θ3 is the number of deviation evaluation indicators; η i is the influencing factor of the i-th deviation evaluation index; v i is the reference value of the i-th deviation evaluation index generated based on the monitoring data packet; Preset deviation evaluation value threshold F1; If f>F1, the current monitoring time node generates a first-level correction instruction for the equipment control strategy.

[0046] Specifically, the deviation evaluation index includes, but is not limited to, the difference between the actual operating load and the expected operating load of each tool and attachment performing the scheduling task, the difference in loading and unloading progress, the work efficiency deviation of each tool and attachment, and other parameters.

[0047] Specifically, the monitoring data package includes the specific execution of the device control strategy Specifically, the larger the deviation evaluation value, the greater the execution deviation of the current equipment control strategy, and timely adjustments are required to ensure the overall loading and unloading efficiency.

[0048] Specifically, the deviation evaluation value threshold can be set according to historical parameters.

[0049] It can be understood that in the above embodiment, a cargo identification sub-model is constructed based on big data analysis to timely identify the characteristic parameters of the cargo to be processed, multiple scheduling strategies are selected according to the characteristic parameters, and the real-time operating status of each tool is obtained according to the status monitoring model to optimize each scheduling strategy, thereby improving the overall scheduling and operation efficiency of the tools, and improving the loading and unloading efficiency and equipment operation efficiency.

[0050] In a preferred embodiment of the present application, when generating the operation risk value of each sub-device according to the preset diagnosis time node, it includes: Preset multiple evaluation cycles, and set the end time node of each evaluation cycle as the diagnosis time node; Set a in sequence according to the sub-device sequence A i is the sub-device to be evaluated; Establish multiple time intervals within the current evaluation cycle according to the monitoring sub-strategy of the sub-device to be evaluated; Generate abnormal evaluation values ​​in each time interval; Establish the abnormal evaluation value sequence G of the sub-equipment to be evaluated, G=(g1,g2…g i …g r ), where g i is the abnormal evaluation value of the i-th sub-device to be evaluated in the i-th time interval; r is the number of time intervals; Generate the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node according to the abnormal evaluation value sequence G; Generate the operation risk value of each sub-equipment in turn; Establish the diagnostic risk value series H at the current diagnostic time node, H = (h1, h2…h i … hn ), where h i is the operating risk value of the i-th sub-device at the current diagnosis time node.

[0051] Specifically, according to the monitoring sub-strategy of the sub-device to be evaluated, a time interval is set between adjacent feedback time nodes. By analyzing the feedback data packets of the sub-device to be evaluated, abnormal evaluation values ​​of each time interval are generated. The larger the abnormal evaluation value, the greater the possibility that the sub-device to be evaluated has a failure risk.

[0052] Specifically, a corresponding diagnosis sub-model is established according to different operating states of the sub-device to be evaluated, and the feedback data packet is analyzed through the diagnosis sub-model to generate an abnormal evaluation value corresponding to the sub-device to be evaluated.

[0053] Specifically, when generating the operation risk value h of the sub-device to be evaluated at the current diagnosis time node, it includes: h=e3*Q3*[ α 1i *k i ]+e4*Q4*[ α 2i *w i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; s1 is the number of abnormal evaluation indicators; α1i is the influencing factor of the i-th abnormal evaluation index; k i is the reference value of the i-th abnormal evaluation index generated based on the abnormal evaluation value sequence G; s2 is the number of equipment risk indicators; α 2i is the influencing factor of the i-th equipment risk index; w i is the reference value of the i-th equipment risk index generated based on the sub-equipment to be evaluated.

[0054] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter in the model is in the same value range.

[0055] Specifically, the abnormal evaluation indicators include but are not limited to the variance, increase and decrease trend, average value and other parameters of the abnormal evaluation value series. By quantifying each abnormal evaluation indicator, each abnormal evaluation indicator is placed in the same value range.

[0056] Specifically, equipment risk indicators include but are not limited to multiple parameters such as the equipment's cumulative operating time, number of failures, and failure frequency.

[0057] Specifically, the larger the operation risk value, the greater the possibility that the sub-equipment to be evaluated has operation risks.

[0058] Specifically, a first operation risk value threshold and a second operation risk value threshold are preset according to historical parameters, wherein the first operation risk value threshold is lower than the second operation risk value threshold. When the operation risk value is greater than the first operation risk value threshold, a first-level warning instruction is generated, and a corresponding maintenance plan is generated according to the operating status of the sub-equipment to be evaluated. If the sub-area to be evaluated is in a working state, maintenance is carried out after the corresponding work is completed. If it is in an idle state, maintenance is carried out immediately.

[0059] Specifically, when the operation risk value is greater than the second risk assessment value threshold, if the sub-device to be assessed is in working condition, the sub-device to be assessed is immediately replaced and repaired.

[0060] It can be understood that in the above embodiment, by establishing a mapping sub-model for each tool, remote monitoring and fault diagnosis of the operating status of each tool can be achieved, and timely warning of the potential failure risks of each tool can be given, thereby improving the efficiency of equipment failure prediction and reducing the overall operation and maintenance cost.

[0061] Based on another preferred embodiment of a method for intelligent management of dock tools based on big data analysis in any of the above preferred embodiments, this preferred embodiment provides a method for intelligent management of dock tools based on big data analysis, including: The central control platform is used to set multiple sub-equipment according to tool parameters and build a status monitoring model and operation scheduling model based on all sub-equipment; A monitoring unit, including a plurality of monitoring submodules, wherein the monitoring submodules are arranged on each sub-device; The monitoring unit is used to collect the operating data of each sub-device and generate feedback data packets for each sub-device; A collection unit, used to obtain parameters of the goods to be processed; The central control platform includes: The first processing module is used to establish a sub-device sequence A, A=(a1, a2…a i …a n ), where a i is the ith sub-device; n is the number of sub-devices; The second processing module is used to build a condition monitoring model and an operation scheduling model; The third processing module is used to set multiple scheduling sub-strategies according to the parameters of the goods to be processed and the operation scheduling model; The third processing module is also used to generate a device control strategy based on the state monitoring model and all scheduling sub-strategies; The early warning module is used to generate the operation risk value of each sub-device according to the preset diagnosis time node, and determine whether to generate an early warning instruction based on all the operation risk values.

[0062] Specifically, the monitoring submodule selects various sensors (pressure, temperature and humidity, GPS) and cameras, and collects the operation data, status data and environmental data of each device in real time through the Internet of Things technology.

[0063] Specifically, the collection unit includes multiple devices that can collect various cargo parameters.

[0064] In a preferred embodiment of the present application, the third processing module is also used for: Obtain the preprocessing result of the cargo identification sub-model on the parameters of the cargo to be processed; Generate cargo feature data package according to preprocessing results; Set up screening sub-strategies based on cargo feature data packages; Filtering in the policy database based on the screening sub-policy, and generating multiple scheduling sub-policies according to the screening results; Establish a scheduling sub-strategy sequence B, B=(b1, b2…b i …b m ), where b i is the i-th scheduling sub-strategy; m is the number of scheduling sub-strategies; Generate scheduling evaluation values ​​of each scheduling sub-strategy in turn; Establish the scheduling evaluation value sequence C, C=(c1, c2…c i…c m ), where c i is the scheduling evaluation value of the i-th scheduling sub-strategy; Set the maximum value c in the scheduling evaluation value sequence C max The corresponding scheduling sub-strategy is a first-level sub-strategy; Generate equipment control strategy based on the first-level sub-strategy and condition monitoring model; Determine whether to generate a correction instruction for the equipment control strategy according to a preset monitoring time node; When the device control strategy is executed, a record data packet is generated; Determine whether to update the policy database based on the recorded data packets.

[0065] In a preferred embodiment of the present application, the early warning module is also used for: Preset multiple evaluation cycles, and set the end time node of each evaluation cycle as the diagnosis time node; Set a in sequence according to the sub-device sequence A i is the sub-device to be evaluated; Establish multiple time intervals within the current evaluation cycle according to the monitoring sub-strategy of the sub-device to be evaluated; Generate abnormal evaluation values ​​in each time interval; Establish the abnormal evaluation value sequence G of the sub-equipment to be evaluated, G=(g1,g2…g i …g r ), where g i is the abnormal evaluation value of the i-th sub-device to be evaluated in the i-th time interval; r is the number of time intervals; Generate the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node according to the abnormal evaluation value sequence G; h=e3*Q3*[ α 1i *k i ]+e4*Q4*[ α 2i *w i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; s1 is the number of abnormal evaluation indicators; α 1i is the influencing factor of the i-th abnormal evaluation index; k i is the reference value of the i-th abnormal evaluation index generated based on the abnormal evaluation value sequence G; s2 is the number of equipment risk indicators; α 2i is the influencing factor of the i-th equipment risk index; w i is the reference value of the i-th equipment risk index generated based on the sub-equipment to be evaluated; Generate the operation risk value of each sub-equipment in turn; Establish the diagnostic risk value series H at the current diagnostic time node, H = (h1, h2…h i … hn ), where h i is the operating risk value of the i-th sub-device at the current diagnosis time node.

[0066] According to the first concept of the present application, a cargo identification sub-model is constructed based on big data analysis to timely identify the characteristic parameters of the cargo to be processed, multiple scheduling strategies are selected according to the characteristic parameters, and the real-time operating status of each tool is obtained according to the status monitoring model to optimize each scheduling strategy, thereby improving the overall scheduling and operation efficiency of the tools, and improving the loading and unloading efficiency and equipment operation efficiency.

[0067] According to the second concept of the present application, by establishing a mapping sub-model for each tool, remote monitoring and fault diagnosis of the operating status of each tool can be achieved, and timely warning of the potential failure risks of each tool can be given, thereby reducing the overall operation and maintenance costs. At the same time, by monitoring the status of each tool, the cargo loading plan can be dynamically optimized in real time, thereby improving the loading and unloading efficiency of cargo.

[0068] 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. An intelligent management method for dock tools based on big data analysis, characterized in that: include: Set multiple sub-equipment according to tool parameters, and build a condition monitoring model and operation scheduling model based on all sub-equipment; Set multiple scheduling sub-strategies according to the parameters of the cargo to be processed and the operation scheduling model, and generate equipment control strategies according to the status monitoring model and all scheduling sub-strategies; Generate the operation risk value of each sub-device according to the preset diagnosis time node, and determine whether to generate an early warning instruction based on all the operation risk values; When setting multiple sub-devices, it includes: Create a sub-device array A, A=(a1,a2…a i …a n ), where a i is the i-th sub-device; n is the number of sub-devices.

2. The intelligent management method for dock tool accessories based on big data analysis according to claim 1, characterized in that: When building a condition monitoring model and running a scheduling model, include: Set a in sequence according to the sub-device sequence A i is the target sub-device; Construct a mapping sub-model for the target sub-device and set a monitoring sub-strategy for the target sub-device; Set multiple feedback time nodes of the target sub-device according to the monitoring sub-strategy; Obtaining a feedback data packet from the target sub-device according to a preset feedback time node; Update the mapping sub-model of the target sub-device according to the feedback data packet; Set the mapping sub-model and monitoring sub-strategy of each sub-device in turn; Construct a state monitoring model based on all mapping sub-models and all monitoring sub-strategies; Generate multiple cargo characteristic indicators based on historical cargo parameters; Construct a cargo identification sub-model based on all cargo characteristic indicators; Generate multiple first-level scheduling strategies based on the historical scheduling parameters of tools and accessories; Build a strategy database based on all first-level scheduling strategies; The operation scheduling model is constructed based on the cargo identification sub-model and the strategy database.

3. The intelligent management method for dock tool accessories based on big data analysis according to claim 2, characterized in that: When multiple scheduling sub-strategies are set according to the parameters of the goods to be processed and the running scheduling model, it includes: The cargo identification sub-model pre-processes the cargo parameters to be processed and generates a cargo feature data packet according to the pre-processing results; Set up screening sub-strategies based on cargo feature data packages; Filtering in the policy database based on the screening sub-policy, and generating multiple scheduling sub-policies according to the screening results; Establish a scheduling sub-strategy sequence B, B=(b1, b2…b i …b m ), where b i is the i-th scheduling sub-strategy; m is the number of scheduling sub-strategies.

4. The intelligent management method for dock tool accessories based on big data analysis according to claim 3, characterized in that: When generating equipment control strategies based on the condition monitoring model and all scheduling sub-strategies, it includes: According to the scheduling sub-strategy sequence B, set bi as the target scheduling sub-strategy in sequence; Generate a scheduling evaluation value c of the target scheduling sub-strategy based on the state monitoring model; c=e1*Q1*[ (β 1i *p i )]+e2*Q2*[ (β 2i *j i )]; Among them, 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 strategy evaluation indicators; β 1i is the influencing factor of the i-th strategy evaluation index set based on the cargo feature data package; p i is the reference value of the i-th strategy evaluation index generated based on the target scheduling sub-strategy; θ2 is the number of operating indicators; β 2i is the influencing factor of the i-th operating indicator; j i is the reference value of the i-th operation evaluation index in the target scheduling sub-strategy generated based on the condition monitoring model; Generate scheduling evaluation values ​​of each scheduling sub-strategy in turn; Establish the scheduling evaluation value sequence C, C=(c1, c2…c i …c m ), where c i is the scheduling evaluation value of the i-th scheduling sub-strategy; Set the maximum value c in the scheduling evaluation value sequence C max The corresponding scheduling sub-strategy is a first-level sub-strategy; Generate equipment control strategy based on the first-level sub-strategy and condition monitoring model; Determine whether to generate a correction instruction for the equipment control strategy according to a preset monitoring time node; When the device control strategy is executed, a record data packet is generated; Determine whether to update the policy database based on the recorded data packets.

5. The intelligent management method for dock tool accessories based on big data analysis according to claim 4, characterized in that: When judging whether to generate a correction instruction for the device control strategy, it includes: Get the monitoring data packet of the current monitoring time node; Generate a deviation evaluation value f of the device control strategy according to the monitoring data packet; f=[ or i *v i ]; Among them, θ3 is the number of deviation evaluation indicators; η i is the influencing factor of the i-th deviation evaluation index; v i is the reference value of the i-th deviation evaluation index generated based on the monitoring data packet; Preset deviation evaluation value threshold F1; If f>F1, the current monitoring time node generates a first-level correction instruction for the equipment control strategy.

6. The intelligent management method for dock tool accessories based on big data analysis according to claim 4, characterized in that: When generating the operation risk value of each sub-device according to the preset diagnosis time node, it includes: Preset multiple evaluation cycles, and set the end time node of each evaluation cycle as the diagnosis time node; Set a in sequence according to the sub-device sequence A i is the sub-device to be evaluated; Establish multiple time intervals within the current evaluation cycle according to the monitoring sub-strategy of the sub-device to be evaluated; Generate abnormal evaluation values ​​in each time interval; Establish the abnormal evaluation value sequence G of the sub-equipment to be evaluated, G=(g1,g2…g i …g r ), where g i is the abnormal evaluation value of the i-th sub-device to be evaluated in the i-th time interval; r is the number of time intervals; Generate the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node according to the abnormal evaluation value sequence G; Generate the operation risk value of each sub-equipment in turn; Establish the diagnostic risk value series H at the current diagnostic time node, H = (h1, h2…h i … hn ), where h i is the operating risk value of the i-th sub-device at the current diagnosis time node.

7. The intelligent management method for dock tool accessories based on big data analysis according to claim 6, characterized in that: When generating the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node, it includes: h=e3*Q3*[ a 1i *k i ]+e4*Q4*[ a 2i *w i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; s1 is the number of abnormal evaluation indicators; α 1i is the influencing factor of the i-th abnormal evaluation index; k i is the reference value of the ith abnormal evaluation index generated based on the abnormal evaluation value sequence G; s2 is the number of equipment risk indicators; α 2i is the influencing factor of the i-th equipment risk index; w i is the reference value of the i-th equipment risk index generated based on the sub-equipment to be evaluated.

8. An intelligent management system for dock tools and equipment based on big data analysis, adopting the intelligent management method for dock tools and equipment based on big data analysis as described in any one of claims 1 to 7, characterized in that: include: The central control platform is used to set multiple sub-equipment according to tool parameters and build a status monitoring model and operation scheduling model based on all sub-equipment; A monitoring unit, comprising a plurality of monitoring submodules, wherein the monitoring submodules are arranged on each sub-device; The monitoring unit is used to collect the operation data of each sub-device and generate a feedback data packet of each sub-device; A collection unit, used to obtain parameters of the goods to be processed; The central control platform includes: The first processing module is used to establish a sub-device sequence A, A=(a1, a2…a i …a n ), where a i is the ith sub-device; n is the number of sub-devices; The second processing module is used to build a condition monitoring model and an operation scheduling model; The third processing module is used to set multiple scheduling sub-strategies according to the parameters of the goods to be processed and the operation scheduling model; The third processing module is also used to generate a device control strategy based on the state monitoring model and all scheduling sub-strategies; The early warning module is used to generate the operation risk value of each sub-device according to the preset diagnosis time node, and determine whether to generate an early warning instruction based on all the operation risk values.

9. The intelligent management system for dock tools and equipment based on big data analysis according to claim 8, characterized in that: The third processing module is further used for: Obtain the preprocessing result of the cargo identification sub-model on the parameters of the cargo to be processed; Generate cargo feature data package according to preprocessing results; Set up screening sub-strategies based on cargo feature data packages; Filtering in the policy database based on the screening sub-policy, and generating multiple scheduling sub-policies according to the screening results; Establish a scheduling sub-strategy sequence B, B=(b1, b2…b i …b m ), where b i is the i-th scheduling sub-strategy; m is the number of scheduling sub-strategies; Generate scheduling evaluation values ​​of each scheduling sub-strategy in turn; Establish the scheduling evaluation value sequence C, C=(c1, c2…c i …c m ), where c i is the scheduling evaluation value of the i-th scheduling sub-strategy; Set the maximum value c in the scheduling evaluation value sequence C max The corresponding scheduling sub-strategy is a first-level sub-strategy; Generate equipment control strategy based on the first-level sub-strategy and condition monitoring model; Determine whether to generate a correction instruction for the equipment control strategy according to a preset monitoring time node; When the device control strategy is executed, a record data packet is generated; Determine whether to update the policy database based on the recorded data packets.

10. The intelligent management system for dock tools and equipment based on big data analysis according to claim 9, characterized in that: The early warning module is also used for: Preset multiple evaluation cycles, and set the end time node of each evaluation cycle as the diagnosis time node; Set a in sequence according to the sub-device sequence A i is the sub-device to be evaluated; Establish multiple time intervals within the current evaluation cycle according to the monitoring sub-strategy of the sub-device to be evaluated; Generate abnormal evaluation values ​​in each time interval; Establish the abnormal evaluation value sequence G of the sub-equipment to be evaluated, G=(g1,g2…g i …g r ), where g i is the abnormal evaluation value of the i-th sub-device to be evaluated in the i-th time interval; r is the number of time intervals; Generate the operation risk value h of the sub-equipment to be evaluated at the current diagnosis time node according to the abnormal evaluation value sequence G; h=e3*Q3*[ a 1i *k i ]+e4*Q4*[ a 2i *w i ]; Among them, e3 is the preset third weight coefficient; e4 is the preset fourth weight coefficient; Q3 is the preset third fixed coefficient; Q4 is the preset fourth fixed coefficient; s1 is the number of abnormal evaluation indicators; α 1i is the influencing factor of the i-th abnormal evaluation index; k i is the reference value of the ith abnormal evaluation index generated based on the abnormal evaluation value sequence G; s2 is the number of equipment risk indicators; α 2i is the influencing factor of the i-th equipment risk index; w i is the reference value of the i-th equipment risk index generated based on the sub-equipment to be evaluated; Generate the operation risk value of each sub-equipment in turn; Establish the diagnostic risk value series H at the current diagnostic time node, H = (h1, h2…h i … hn ), where h i is the operating risk value of the i-th sub-device at the current diagnosis time node.

Images