A port machine equipment intelligent management method and system based on an internet of things

Abstract

The application provides a port machine equipment intelligent management method and system based on the Internet of Things, and relates to the technical field of intelligent management of port machinery. The method comprises the following steps: collecting multi-dimensional operation monitoring data through a port machine intelligent edge controller; performing protocol normalization and cleaning processing on the multi-dimensional operation monitoring data and converting the multi-dimensional operation monitoring data into standard Internet of Things data; transmitting and storing the standard Internet of Things data to a unified intelligent port machine Internet of Things platform; calling a big data analysis tool and an AI model to analyze the equipment state, count the load and predict potential faults of the standard Internet of Things data, and generating an equipment health report; and issuing a remote debugging instruction to the port machine intelligent edge controller by the unified intelligent port machine Internet of Things platform to remotely control and manage the port machine equipment, so that the overall intelligent management of the port machine equipment is realized, potential equipment faults are identified in a timely manner, the predictive maintenance capability of the equipment is improved, the data island phenomenon is solved, the equipment operation efficiency is improved, and the fault downtime is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent management of port machinery, and particularly relates to a port machinery equipment intelligent management method and system based on the Internet of Things. BACKGROUND

[0002] Port machinery equipment intelligent management is a key link of port intelligent operation.

[0003] At present, port machinery equipment management still widely relies on manual inspection and experience judgment, and has problems of low efficiency and poor reliability. Although the prior art has tried to collect data and monitor the state by means of sensors, there is a lack of a unified data processing and analysis platform, and it is difficult to realize comprehensive intelligent management of equipment. The traditional method uses a PLC control system to locally monitor the equipment state, and performs equipment maintenance through manual regular inspection or a simple alarm mechanism based on rules. The existing local monitoring mode has a serious information island phenomenon, cannot realize data integration and deep analysis across equipment and systems, and has a lagging response of manual maintenance, cannot be remotely controlled, is difficult to identify potential faults in time, and lacks a predictive maintenance strategy, so that the equipment failure rate is high, which seriously affects the port operation efficiency and production safety.

[0004] Therefore, it is necessary to provide a port machinery equipment intelligent management method and system based on the Internet of Things to solve the above technical problems. SUMMARY

[0005] To solve the above technical problems, the present application provides a port machinery equipment intelligent management method and system based on the Internet of Things to solve the problems that the prior art cannot realize comprehensive intelligent management of equipment, has a serious equipment data island phenomenon, is difficult to identify potential faults, lacks a predictive maintenance strategy, and has low equipment operation efficiency.

[0006] The present application provides a port machinery equipment intelligent management method based on the Internet of Things, which comprises:

[0007] Multi-dimensional operation monitoring data is collected by a port machinery intelligent edge controller on the port machinery equipment, including electrical parameters, working condition data and environmental data;

[0008] The port machinery intelligent edge controller performs protocol normalization and cleaning processing on the multi-dimensional operation monitoring data, and converts the data into standard Internet of Things data;

[0009] The standard Internet of Things data is transmitted and stored to a unified intelligent port machinery Internet of Things platform of B / S architecture through an optical fiber;

[0010] The unified intelligent port machinery Internet of Things platform calls a big data analysis tool and an AI model, performs equipment state analysis, load statistics and potential fault prediction on the standard Internet of Things data, and generates an equipment health report;

[0011] Based on the device health report, the unified port machine Internet of Things platform issues a remote debugging instruction to the port machine intelligent edge controller to remotely control and manage the port machine.

[0012] Preferably, the electrical parameters include the breaker state, contactor state, and frequency converter operating parameters of the port machine; the working condition data include the mechanism position, running time, and work volume data of the port machine; and the environmental data include the real-time wind speed and real-time temperature at the location of the port machine.

[0013] The work volume data is corrected in real time by a dynamic correction algorithm based on multi-source error compensation, and the corrected work volume data is As follows:

[0014] In the formula, represents the work volume data of the port machine before correction; represents the pth multi-source error compensation coefficient of the port machine; represents the product of all multi-source error compensation coefficients; represents the aging correction amount of the port machine, , represents the used time length of the port machine, represents the design life of the port machine; represents the mechanism posture compensation coefficient of the port machine; represents the amplitude angle of the variable amplitude mechanism; represents the yaw angle of the rotating mechanism; represents the wind speed compensation coefficient of the port machine; represents the exponential function with the natural constant e as the base; represents the real-time wind speed at the location of the port machine; represents the environmental temperature compensation coefficient; represents the real-time temperature; represents the standard temperature; represents the power supply voltage compensation coefficient; represents the real-time power supply power; represents the rated power supply power.

[0015] Preferably, the port machine intelligent edge controller performs protocol normalization and cleaning processing on the multi-dimensional operation monitoring data, and converts the data into standard Internet of Things data, specifically including:

[0016] The multi-protocol communication bus interface of the port machine intelligent edge controller performs protocol normalization processing on the multi-dimensional operation monitoring data;

[0017] The multi-dimensional operation monitoring data is subjected to outlier rejection, missing value completion and data denoising cleaning processing;

[0018] The multi-dimensional operation monitoring data subjected to protocol normalization and cleaning processing is converted into the standard Internet of Things data.

[0019] Preferably, in the process of transmitting the standard Internet of Things data to the unified intelligent port machine Internet of Things platform of B / S architecture through an optical fiber, a local cache mechanism is started when the network is interrupted, the standard Internet of Things data is stored in chronological order according to the time stamp, and the data recovery mechanism of the cache data is automatically triggered after the network connection;

[0020] Based on the cache data recovery mechanism, the integrity of the cached standard Internet of Things data is checked, including checking the continuity of the time stamp and verifying the data integrity through the hash value, and after the checking, the cached standard Internet of Things data is uploaded by using a double-priority transmission algorithm based on time priority and data importance;

[0021] The calculation formula of the transmission level of the cached standard Internet of Things data d is as follows:

[0022] In the formula, represents the transmission level of the cached standard Internet of Things data d; represents the time priority weight of the cached standard Internet of Things data; represents the data importance weight of the cached standard Internet of Things data, and ; represents the storage time stamp of the cached standard Internet of Things data d; represents the network connection time stamp; represents the data importance score of the cached standard Internet of Things data d; represents the data importance score weight of the kth sub-standard Internet of Things data; represents the data importance score of the kth sub-standard Internet of Things data, k=1, represents the data importance score of the 1st sub-standard Internet of Things data, i.e., the running fault data of the port machine device, k=2, represents the data importance score of the 2nd sub-standard Internet of Things data, i.e., the key working condition data of the port machine device, k=3, represents the data importance score of the 3rd sub-standard Internet of Things data, i.e., the real-time environmental data of the location of the port machine device.

[0023] Preferably, the AI model is deployed in the cloud AI computing cluster of the unified intelligent port machine Internet of Things platform, and supports network model conversion based on the TensorFlow framework.

[0024] The device state analysis calculates device state analysis indexes of the port machinery device by multi-dimensional statistics on the standard Internet of Things data.

[0025] The load statistics calculates the average load, peak load and load distribution of the port machinery device in a unit time by aggregating calculation on the standard Internet of Things data, and identifies whether the port machinery device is overloaded or insufficiently loaded.

[0026] The potential fault prediction identifies potential fault data of the port machinery device by learning the change trend of the standard Internet of Things data, in combination with historical fault data and wear rules of the port machinery device, and predicts the dynamic maintenance period and residual life of the port machinery device.

[0027] Preferably, the calculation of the device state analysis indexes adopts an improved device comprehensive efficiency algorithm based on effective operation time, and the device state analysis indexes include port machinery device effective utilization rate , port machinery device effective operation time and port machinery device performance efficiency coefficient , and the corresponding calculation formulas are as follows: In the formula, represents the number of operation cycles of the port machinery device in the statistical period; represents the total time of the i-th operation cycle; represents the idling time of the port machinery device in the statistical period; represents the fault downtime of the port machinery device in the statistical period; represents the number of effective operations of the port machinery device in the statistical period; represents the actual time of the s-th effective operation; represents the actual operation amount of the s-th effective operation; represents the rated operation amount of the s-th effective operation; represents the positioning adjustment time in the s-th effective operation; represents the number of running mechanisms of the port machinery device; represents the rated speed of the g-th running mechanism; represents the actual running speed of the g-th running mechanism; represents the average rated speed of all running mechanisms, ; and represents the total speed deviation of all running mechanisms.

[0028] Preferably, the calculation of the dynamic maintenance period and the residual life adopts a dynamic fuzzy programming algorithm based on residual life, and the corresponding calculation formulas are as follows:

[0029] In the formula, represents the safety redundancy coefficient of the port machinery equipment; represents the failure influence coefficient of the port machinery equipment, ; represents the number of historical failure types of the port machinery equipment; represents the severity coefficient of the i-th historical failure of the port machinery equipment, i=1, represents the severity coefficient of the 1st historical failure of the port machinery equipment, i.e. the mild failure, and , , represents the severity coefficient of the 2nd historical failure of the port machinery equipment, i.e. the moderate failure, and , , represents the severity coefficient of the 3rd historical failure of the port machinery equipment, i.e. the severe failure, and ; represents the design life of the port machinery equipment; represents the used time length of the port machinery equipment; represents the j-th remaining life correction factor of the port machinery equipment, j=1, represents the 1st remaining life correction factor of the port machinery equipment, i.e. the failure frequency correction factor, j=2, represents the 2nd remaining life correction factor of the port machinery equipment, i.e. the overload time length correction factor, j=3, represents the 3rd remaining life correction factor of the port machinery equipment, i.e. the maintenance quality correction factor; represents the product of the remaining life correction factors of the port machinery equipment; represents the historical failure times of the port machinery equipment; represents the historical operation times of the port machinery equipment; represents the historical overload running time length of the port machinery equipment; represents the historical total running time length of the port machinery equipment; represents the historical qualified time length of the maintenance of the port machinery equipment; represents the historical total interval time length of the maintenance of the port machinery equipment.

[0030] Preferably, the method further comprises: using an improved particle swarm-gray wolf hybrid algorithm based on target constraints to optimize the energy consumption of the remote control and management operation of the port machinery equipment, and the corresponding calculation formula is as follows:

[0031] In the formula, represents the energy consumption-time delay comprehensive optimization target function; represents the energy consumption weight; latency weight, ; total energy consumption of remote control and management operation; number of sub-operations of remote control and management operation; operation amount of the i-th sub-operation; total latency of remote control and management operation; duration of the i-th sub-operation; real-time power of the port machinery equipment; rated power of the port machinery equipment; real-time load rate of the port machinery equipment; real-time speed of the j-th port machinery equipment action; maximum speed of the j-th port machinery equipment action; real-time wind speed of the location of the port machinery equipment; minimum operation amount of the i-th sub-operation.

[0032] A port machinery equipment intelligent management system based on Internet of Things, comprising:

[0033] A data acquisition module is configured to acquire multi-dimensional operation monitoring data including electrical parameters, working condition data and environmental data through a port machine intelligent edge controller on the port machinery equipment.

[0034] A data preprocessing module is configured to perform protocol normalization and cleaning processing on the multi-dimensional operation monitoring data by the port machine intelligent edge controller, and convert the data into standard Internet of Things data.

[0035] A transmission and storage module is configured to transmit and store the standard Internet of Things data to a unified intelligent port machine Internet of Things platform of B / S architecture through optical fibers.

[0036] A report generation module is configured to call a big data analysis tool and an AI model by the unified intelligent port machine Internet of Things platform to perform equipment state analysis, load statistics and potential fault prediction on the standard Internet of Things data, and generate an equipment health report.

[0037] A remote debugging module is configured to issue a remote debugging instruction to the port machine intelligent edge controller by the unified intelligent port machine Internet of Things platform based on the equipment health report, and perform remote control and management on the port machinery equipment.

[0038] Compared with the related art, the port machinery equipment intelligent management method and system based on Internet of Things provided by the present application has the following beneficial effects:

[0039] The application collects multi-dimensional operation monitoring data on the port machine equipment through the port machine intelligent edge controller, including electrical parameters, working condition data and environmental data; the port machine intelligent edge controller performs protocol normalization and cleaning processing on the multi-dimensional operation monitoring data, and converts the multi-dimensional operation monitoring data into standard Internet of Things data; the standard Internet of Things data is transmitted and stored to the unified intelligent port machine Internet of Things platform of B / S architecture through optical fibers; the unified intelligent port machine Internet of Things platform calls a big data analysis tool and an AI model to analyze the equipment state, count the load and predict potential faults of the standard Internet of Things data, and generates an equipment health report; based on the equipment health report, the unified intelligent port machine Internet of Things platform issues a remote debugging instruction to the port machine intelligent edge controller to remotely control and manage the port machine equipment, so that the overall intelligent management of the port machine equipment can be realized, potential equipment faults can be identified in time, the predictive maintenance capability of the equipment is improved, the equipment data island phenomenon is effectively solved, the equipment operation efficiency is significantly improved, and the fault downtime is reduced.

[0040] The application deploys a port machine intelligent edge controller, is compatible with a multi-protocol communication bus interface, collects and performs protocol normalization processing on multi-dimensional operation monitoring data, effectively overcomes the disadvantages of isolated port machine equipment data and non-uniform format, and improves the usability of data and system integration. The edge controller has the ability of data cleaning, can perform real-time processing on abnormal values and missing values, and combines optical fiber transmission and offline cache data recovery mechanism to guarantee the integrity and time sequence consistency of data in the transmission process, significantly improves the robustness and data reliability of the system. The unified intelligent port machine Internet of Things platform integrates a big data analysis tool and an AI model, can perform multi-dimensional evaluation on the equipment state, accurately calculates key indicators such as effective utilization rate and performance efficiency of the equipment, simultaneously performs load statistics on the port machine equipment, identifies whether there is overload or insufficient load, and realizes early identification and residual life prediction of potential faults based on historical data and real-time trends, significantly improves the initiative and predictability of equipment maintenance. The unified intelligent port machine Internet of Things platform issues a remote debugging instruction according to the equipment health report to realize accurate control and dynamic management of the port machine equipment. By introducing an improved particle swarm-gray wolf hybrid algorithm based on target constraints, the work efficiency is guaranteed while the energy consumption is effectively reduced, and the overall economy and sustainability of port operation are improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A flowchart of a port machine equipment intelligent management method based on an Internet of Things provided for an embodiment of the application;

[0042] Figure 2 A system block diagram of a port machine equipment intelligent management system based on an Internet of Things provided for an embodiment of the application;

[0043] Figure 3A hardware structure schematic diagram of an electronic device provided by an embodiment of the present application is provided. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, any other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0045] As Figure 1 shown is a flowchart of a port machine equipment intelligent management method based on an Internet of Things provided by an embodiment of the present application, Figure 1 The execution subject of the method shown can be a software and / or a hardware device. The execution subject of the present application can include but is not limited to at least one of the following: a user equipment, a network equipment, and the like. The user equipment can include but is not limited to a computer, a smart phone, a personal digital assistant (PDA), and the above-mentioned electronic equipment, and the like. The network equipment can include but is not limited to a single network server, a server group composed of multiple network servers, or a cloud composed of a large number of computers or network servers based on cloud computing, wherein the cloud computing is a kind of distributed computing, and a super virtual computer composed of a loose-coupled computer group. The present embodiment does not make any limitation. The steps S1 to S5 are included, and are specifically as follows:

[0046] S1, collecting multi-dimensional operation monitoring data including electrical parameters, working condition data, and environmental data through a port machine intelligent edge controller on a port machine equipment;

[0047] The port machine equipment refers to large mechanical equipment used for loading and unloading operations in a port, such as a portal crane, a ship loader, a bucket wheel stacker-reclaimer, and the like. The port machine intelligent edge controller is a core equipment connecting the port machine equipment and a unified intelligent port machine Internet of Things platform, is deployed locally on the port machine equipment, and is an industrial control device responsible for data collection, protocol conversion, data analysis and processing, can realize data interaction and remote control management, and ensures high-speed and stable operation of the port machine equipment.

[0048] The electrical parameters include a circuit breaker state, a contactor state, and frequency converter operation parameters of the port machine equipment; the working condition data includes mechanism position, operation duration, and work quantity data of the port machine equipment; and the environmental data includes real-time wind speed and real-time temperature of a position where the port machine equipment is located;

[0049] For example, in the operation monitoring process of the portal crane, multiple types of key information of the portal crane equipment are collected through the PLC, including equipment working condition data, equipment mode, emergency stop state, fault protection related data, and electrical parameters. Among them, the equipment mode includes grab bucket mode, hook double machine mode, hook single machine 1 mode, hook single machine 2 mode, remote control mode, local control mode, etc., and the fault protection related data includes phase sequence detection result, overload signal, overspeed signal, limit trigger condition, etc. At the same time, through data operation of the intelligent edge controller of the portal crane, the core operation indexes such as equipment running time, energy consumption in the operation process, and actual utilization rate of equipment are further obtained.

[0050] In the operation monitoring process of the ship loader, an absolute encoder and an angle sensor are additionally installed, which are connected to the original PLC or the newly added Internet of Things control terminal of the equipment, so as to realize real-time collection and monitoring of key position parameters such as the pitch angle, rotation angle, and arm stretching position of the ship loader.

[0051] Among them, the dynamic correction algorithm based on multi-source error compensation is used to correct the operation data in real time, and the corrected operation data As follows:

[0052] In the formula, represents the operation data of the portal crane equipment before correction; represents the pth multi-source error compensation coefficient of the portal crane equipment; represents the product of all multi-source error compensation coefficients; represents the aging correction amount of the portal crane equipment, , represents the used time of the portal crane equipment, represents the design life of the portal crane equipment; represents the mechanism posture compensation coefficient of the portal crane equipment; represents the amplitude angle of the luffing mechanism; represents the yaw angle of the rotating mechanism; represents the wind speed compensation coefficient of the portal crane equipment; represents the exponential function with the natural constant e as the base; represents the real-time wind speed at the location of the portal crane equipment; represents the environmental temperature compensation coefficient; represents the real-time temperature; represents the standard temperature; represents the power supply voltage compensation coefficient; represents the real-time power supply power; represents the rated power supply power.

[0053] In practical applications, the multi-source error compensation coefficient needs to be determined in combination with historical operation data of the port machinery equipment and actual error statistical results, and corresponding coefficients are set for different error sources to ensure that each error factor can be accurately compensated, and the product of all coefficients can comprehensively quantify the overall influence degree of multi-source errors on the operation data.

[0054] In the aging correction amount calculation, the service time is obtained through the cumulative timing data of the port machinery equipment operation log, and the design life is obtained by referring to the life parameters of the core components in the equipment factory technical document. The ratio of the two can intuitively reflect the aging degree of the equipment, and then determine the correction range of the operation quantity measurement caused by aging.

[0055] The mechanism posture compensation coefficient is linked with the amplitude angle of the amplitude mechanism and the yaw angle of the rotation mechanism. The amplitude angle and the yaw angle are collected in real time by the equipment posture sensor. The larger the angle deviation is, the larger the adjustment range of the compensation coefficient is, so as to correct the operation quantity measurement deviation caused by the change of the mechanism posture.

[0056] The wind speed compensation coefficient is set in combination with the historical wind speed data of the port and the safety threshold of the equipment operation. The real-time wind speed is obtained by the wind speed sensor deployed on the top of the port machinery equipment. The exponential function is used to build the correlation between wind speed and compensation coefficient, so as to avoid the distortion of operation quantity statistics in strong wind or gust environment.

[0057] The environmental temperature compensation coefficient is calculated by the difference between the real-time temperature and the standard temperature, which corrects the influence of temperature change on the measurement accuracy of electrical components.

[0058] The power supply voltage compensation coefficient is derived based on the ratio of real-time power supply power to rated power supply power. The real-time power supply power is calculated by the voltage and current data collected by the port machinery intelligent edge controller, so as to effectively offset the operation quantity measurement deviation caused by unstable power supply. Finally, through multi-dimensional compensation correction, the accuracy of operation quantity data is ensured.

[0059] The dynamic correction algorithm based on multi-source error compensation can real-time offset the multi-source errors of port machinery operation data, correct the measurement deviation caused by equipment aging, eliminate the interference of mechanism posture change, wind speed fluctuation, environmental temperature anomaly on data, make up the measurement distortion caused by unstable power supply, and ensure the accuracy of operation quantity data.

[0060] S2, the port machinery intelligent edge controller performs protocol normalization and cleaning processing on the multi-dimensional operation monitoring data, and converts the multi-dimensional operation monitoring data into standard Internet of Things data;

[0061] The port machinery intelligent edge controller performs protocol normalization and cleaning processing on the multi-dimensional operation monitoring data, and converts the multi-dimensional operation monitoring data into standard Internet of Things data, specifically including:

[0062] The multi-protocol communication bus interface of the port machine intelligent edge controller performs protocol normalization processing on the multi-dimensional operation monitoring data.

[0063] The multi-dimensional operation monitoring data is subjected to outlier rejection, missing value completion, and data denoising cleaning processing.

[0064] The multi-dimensional operation monitoring data after protocol normalization and cleaning processing is converted into the standard Internet of Things data.

[0065] The multi-protocol communication bus interface supports mainstream industrial communication protocols such as Profibus, Profinet, and Ethercat, to adapt to the communication needs of different manufacturers and different types of sensing and industrial control devices in port machine equipment. Through the built-in protocol analysis and conversion module, heterogeneous multi-dimensional operation monitoring data is unified into standard Internet of Things data recognizable by the port machine intelligent edge controller, thereby realizing protocol normalization processing of multi-source data.

[0066] Outlier rejection identifies data that exceeds the reasonable range based on the 3σ criterion and removes it, such as identifying and removing wind speed data that is far beyond the safety operating threshold of port machine equipment, and sudden rise and fall of current and voltage data. Missing value completion is based on linear interpolation of valid data at adjacent times or mean value method of historical similar working condition data. Data denoising filters out electromagnetic interference signals introduced during transmission of sensing devices through wavelet transform. Standard Internet of Things data is encapsulated in JSON format, including data identification, collection timestamp, device number, and monitoring parameter value fields, to ensure that the data can be directly connected to the unified smart port machine Internet of Things platform and meet the standardization requirements of the unified smart port machine Internet of Things platform for data format.

[0067] S3, through the optical fiber, transmits and stores the standard Internet of Things data to the unified smart port machine Internet of Things platform of B / S architecture;

[0068] During the process of transmitting the standard Internet of Things data to the unified smart port machine Internet of Things platform of B / S architecture through the optical fiber, when the network is interrupted, the local cache mechanism is started, and the standard Internet of Things data is stored in chronological order. After network connection, the offline cache data recovery mechanism is automatically triggered;

[0069] Based on the offline cache data recovery mechanism, the cached standard Internet of Things data is subjected to integrity verification, including verifying the continuity of the timestamp and verifying the data integrity through the hash value. After verification, the cached standard Internet of Things data is uploaded using a dual-priority transmission algorithm based on time priority and data importance;

[0070] The timestamp continuity check is passed by comparing whether the interval of adjacent timestamps of the cache data conforms to the preset collection period. If the interval is abnormal, the missing data segment is marked. Subsequently, whether it needs to be supplemented is determined in combination with the historical data law. The hash value verification is passed by comparing the hash values of the cache data and the original standard Internet of Things data, so as to ensure that the data is not tampered with or damaged due to device failure, electromagnetic interference and the like in the local storage process.

[0071] It should be noted that the time priority is sorted according to the collection timestamp of the cache data, and the data in the earlier network interruption period is preferentially uploaded, so as to avoid the influence of data time sequence disorder on the coherent analysis of the running state of the port machine device by the unified intelligent port machine Internet of Things platform. The data importance priority is divided according to the data type, the data directly related to the safe operation of the device such as the fault signal of the circuit breaker and the overload signal is set as high priority, and the conventional temperature and humidity data in the environmental data is set as ordinary priority. The high-priority data preferentially occupies the bandwidth in the transmission queue, so as to ensure that the key data is preferentially sent to the unified intelligent port machine Internet of Things platform, and to support the platform to respond to the abnormal situation of the device in time.

[0072] The calculation formula of the transmission level of the cache standard Internet of Things data d is as follows:

[0073] In the formula, indicates the transmission level of the cache standard Internet of Things data d; indicates the time priority weight of the cache standard Internet of Things data; indicates the data importance weight of the cache standard Internet of Things data, and ; indicates the storage timestamp of the cache standard Internet of Things data d; indicates the network connection timestamp; indicates the data importance score of the cache standard Internet of Things data d; indicates the data importance score weight of the kth substandard Internet of Things data; indicates the data importance score of the kth substandard Internet of Things data, when k=1, indicates the data importance score of the 1st substandard Internet of Things data, i.e. the running fault data of the port machine device, when k=2, indicates the data importance score of the 2nd substandard Internet of Things data, i.e. the key working condition data of the port machine device, when k=3, indicates the data importance score of the 3rd substandard Internet of Things data, i.e. the real-time environmental data of the position of the port machine device.

[0074] The values of the time priority weight and the data importance weight are determined in combination with the port machine operation data management requirements, and the sum of the two is 1. The storage timestamp and the network connection timestamp are both accurate to seconds, and are recorded synchronously through a clock module of a port machine intelligent edge controller, so that the time bases of the two are consistent, thereby providing an accurate basis for calculating the data cache duration.

[0075] The data importance score weight is configured differently according to the differences between the sub-standard Internet of Things data types, and the importance score of each sub-standard Internet of Things data is determined according to the influence degree on the safe operation of the equipment and the evaluation of the operation efficiency. For each sub-standard Internet of Things data, the operation fault data is directly related to the safe operation of the equipment, the key working condition data is used to support the evaluation of the operation efficiency of the equipment, and the real-time environment data is auxiliary monitoring data. The sum of the importance score weights of each sub-standard Internet of Things data is 1, which can ensure the rationality and consistency of the quantitative allocation of the weight, and avoid the deviation of the priority of the transmission of key data due to the imbalance of the weight. Finally, the total importance score is calculated by the product of the data importance score weight and the data importance score, so as to ensure that the calculation of the transmission level accurately matches the actual application value of the data.

[0076] It can be understood that by quantifying the transmission level of the standard Internet of Things data, the orderly uploading of the standard Internet of Things data after the network is disconnected is facilitated. Specifically, first, the time priority weight, the storage timestamp and the network connection timestamp are combined to accurately quantify the data cache duration, so as to ensure that the cached data generated earlier is uploaded first, avoid the confusion of the data time sequence, ensure that the unified intelligent port machine Internet of Things platform cannot analyze the running state of the port machine equipment coherently, and protect the time sequence integrity of the data; second, according to the data importance weight and the sub-data score, the transmission priority of different types of data is determined, so that the key data such as equipment safety fault and core working condition can occupy the transmission resources preferentially, so as to ensure that the unified intelligent port machine Internet of Things platform can obtain the core information of the port machine safety and operation in the first time, respond to equipment abnormalities in time, support operation and maintenance decisions, and balance the data transmission efficiency and practicability.

[0077] S4, the unified intelligent port machine Internet of Things platform calls a big data analysis tool and an AI model to perform equipment state analysis, load statistics and potential fault prediction on the standard Internet of Things data, and generates an equipment health report;

[0078] The AI model is deployed in a cloud AI computing cluster of the unified intelligent port machine Internet of Things platform, and supports network model conversion based on a TensorFlow framework.

[0079] The equipment state analysis calculates equipment state analysis indexes of the port machine equipment by performing multi-dimensional statistics on the standard Internet of Things data.

[0080] The load statistics are calculated by aggregating the standard Internet of Things data to count the average load, peak load and load distribution of the port machinery equipment in a unit time, to identify whether the port machinery equipment is overloaded or underloaded.

[0081] The potential fault prediction identifies the potential fault data of the port machinery equipment by learning the change trend of the standard Internet of Things data, combining the historical fault data and wear law of the port machinery equipment, to predict the dynamic maintenance cycle and remaining life of the port machinery equipment.

[0082] The big data analysis tool can efficiently process massive standard Internet of Things data, realize data sharding storage and parallel computing, and guarantee the efficiency of multi-dimensional statistics and aggregation calculation. The cloud AI computing cluster is configured with a GPU acceleration module, which performs inference optimization on the model converted by the TensorFlow framework, shortens the time consumption of AI model analysis and prediction, and adapts to the real-time monitoring requirements of port machinery equipment.

[0083] The calculation of the equipment state analysis index adopts an improved equipment comprehensive efficiency algorithm based on effective working time, which quickly analyzes the state of the port machinery equipment by calculating the effective utilization rate of the port machinery equipment, the effective working time of the port machinery equipment and the performance efficiency coefficient of the port machinery equipment.

[0084] The load statistics first integrate and process the standard Internet of Things data, and then extract and count the average load, peak load and load distribution of the port machinery equipment in a unit time based on the set unit time dimension.

[0085] The average load reflects the overall running load level of the equipment in a unit time, the peak load reflects the maximum load intensity in the equipment operation, and the load distribution presents the running proportion of different load intervals. Through the comprehensive analysis of these three types of statistical results, it can be accurately identified whether there is a problem of overload or underload in the operation of the port machinery equipment. If the equipment load exceeds the conventional reasonable range, it is determined to be overloaded; if it is in a low load state for a long time and there is no reasonable work planning, it is determined to be underloaded.

[0086] In predicting potential faults, the historical fault data need to include the fault occurrence time, fault type and corresponding data characteristics of the same type of components of the port machinery equipment in the past 5 years, and the wear law is derived by combining the material parameters of the core components of the equipment and the actual running load. The identified potential fault data includes wind speed compensation anomalies, continuous current threshold value exceeding, etc.

[0087] The calculation of the dynamic maintenance period and the residual life adopts a dynamic fuzzy programming algorithm based on the residual life, wherein the dynamic maintenance period is adjusted according to the potential fault risk level, a high-risk fault corresponds to a shortened maintenance interval, and a low-risk fault is maintained according to a normal period. In the calculation of the residual life, the basic life data is corrected by the product of the fault frequency correction factor, the overload time correction factor and the maintenance quality correction factor in combination with the design life of the port machinery equipment and the used time, and the final residual life is obtained by referring to the life data of similar components.

[0088] The device state analysis result, the load statistical condition, the fault prediction conclusion and the maintenance suggestion and the comprehensive health degree result are integrated to generate a device health report, so as to provide an intuitive and accurate decision basis for the port machinery operation and maintenance personnel.

[0089] The calculation of the device state analysis index adopts an improved device comprehensive efficiency algorithm based on the effective operation time, and the device state analysis index includes the port machinery device effective utilization rate , the port machinery device effective operation time and the port machinery device performance efficiency coefficient , and the corresponding calculation formulas are as follows: In the formula, represents the operation cycle number of the port machinery device in the statistical period; represents the total time of the i-th operation cycle; represents the idle standby time of the port machinery device in the statistical period; represents the fault downtime of the port machinery device in the statistical period; represents the effective operation number of the port machinery device in the statistical period; represents the actual time of the s-th effective operation; represents the actual operation amount of the s-th effective operation; represents the rated operation amount of the s-th effective operation; represents the positioning adjustment time in the s-th effective operation; represents the number of running mechanisms of the port machinery device; represents the rated speed of the g-th running mechanism; represents the actual running speed of the g-th running mechanism; represents the average rated speed of all running mechanisms, ; and represents the speed deviation sum of all running mechanisms.

[0090] The statistical period can be set as day, week or month according to the port machine operation management requirement, to ensure that the index calculation is in line with the actual operation rhythm. The operation cycle number is counted by the complete operation process recorded by the port machine intelligent edge controller, and the total duration of each operation cycle is obtained by the time stamp difference in the equipment operation log. The idle time of the empty standby needs to exclude the reasonable pause time of the normal operation interval of the equipment, and only the idle time when there is no operation task is counted, and the fault downtime is determined in combination with the equipment fault alarm record and the downtime timestamp, to ensure the accuracy of the effective operation time calculation. The effective operation number takes the operation process that completes the preset operation amount threshold as the statistical standard, and the actual operation amount and the rated operation amount are determined according to the operation type corresponding to the measurement standard of the port machine equipment. The positioning adjustment time is obtained by accumulating the mechanism alignment calibration time recorded by the sensor. The number of running mechanisms is determined according to the type of port machine equipment, such as portal crane which needs to count four types of mechanisms, i.e. lifting, amplitude changing, rotating and walking. The rated speed of each running mechanism is referred to the factory technical parameters of the equipment, and the actual running speed is calculated in real time by the mechanism running data collected by the edge controller. The average rated speed of all running mechanisms is obtained by the arithmetic mean of the rated speed of each mechanism, and the speed deviation sum is obtained by accumulating the absolute value of the difference between the actual running speed and the rated speed of each mechanism. Finally, the effective utilization rate, effective operation time and performance efficiency coefficient of the equipment are accurately calculated by the above parameters, which fully reflects the running state of the port machine.

[0091] The dynamic maintenance period and the calculation of the remaining life adopt a dynamic fuzzy planning algorithm based on the remaining life, and the corresponding calculation formula is as follows:

[0092] In the formula, represents the safety redundancy coefficient of the port machine equipment; represents the fault influence coefficient of the port machine equipment, ; represents the number of historical fault types of the port machine equipment; represents the severity coefficient of the i-th historical fault of the port machine equipment, i=1, represents the severity coefficient of the first historical fault of the port machine equipment, i.e. the severity coefficient of the mild fault, and , , represents the severity coefficient of the second historical fault of the port machine equipment, i.e. the severity coefficient of the moderate fault, and , , represents the severity coefficient of the third historical fault of the port machine equipment, i.e. the severity coefficient of the severe fault, and ; represents the design life of the port machine equipment; represents the used time of the port machine equipment; The first residual life correction factor of the port machinery equipment, j=1, The first residual life correction factor of the port machinery equipment, j=1, The second residual life correction factor of the port machinery equipment, j=2, The third residual life correction factor of the port machinery equipment, j=3, The product of the residual life correction factors of the port machinery equipment; The historical failure times of the port machinery equipment; The historical operation times of the port machinery equipment; The historical overload running time of the port machinery equipment; The historical total running time of the port machinery equipment; The historical qualified time of the port machinery equipment maintenance; The historical total interval time of the port machinery equipment maintenance.

[0093] The safety redundancy coefficient is set according to the risk level of the port machinery equipment operation scene, and the equipment in the busy operation area of the port or bearing heavy cargo takes a higher value, and the equipment in the conventional operation scene takes a basic value, which is used to buffer the influence of failure risk on life calculation. The failure influence coefficient is determined in combination with the influence degree of the equipment after shutdown on the port operation, and the coefficient value of the core operation equipment is higher, and the coefficient value of the non-core auxiliary equipment is relatively lower. The historical failure type quantity statistics need to exclude repeated failure records, and only count different types of failure categories. The severity coefficients of light, moderate and severe failures are divided by the downtime caused by the failure, the maintenance cost and the damage degree to the performance of the equipment, so as to ensure that the coefficients match the actual influence of the failure.

[0094] In the residual life correction factor, the failure frequency correction factor is calculated by the ratio of the historical failure times to the historical operation times, the overload time correction factor is determined by the proportion of the historical overload running time to the historical total running time, and the maintenance quality correction factor is derived according to the ratio of the maintenance historical qualified time to the maintenance historical total interval time. The product of each correction factor can comprehensively quantify the influence of the actual operation condition of the equipment on the residual life, and finally combined with the design life and the used time, the dynamic maintenance cycle and the residual life are accurately calculated.

[0095] S5, based on the equipment health report, the unified intelligent port machinery Internet of Things platform issues a remote debugging instruction to the port machinery intelligent edge controller, and remotely controls and manages the port machinery equipment.

[0096] It can be understood that the remote debugging instruction covers the device parameter adjustment instruction, the running mode switching instruction and the fault early warning disposal instruction. The parameter adjustment instruction is accurate calibration for the core components of the port machine, and ensures that the component running parameters match the current operation demand. The running mode switching instruction supports flexible switching of the device between remote control and local control modes, and adapts to the operation demand in different operation scenarios. The fault early warning disposal instruction is aimed at the potential faults identified in the device health report, and issues pre-disposal parameters, such as reducing the running power of high-load components and avoiding the risk of fault expansion in advance.

[0097] After the port machine intelligent edge controller receives the instruction, it first checks the integrity and compliance of the instruction, confirms that there is no parameter conflict or logical error, and then converts the instruction into a signal recognizable by the device industrial control system to drive the actuator to act. At the same time, the port machine intelligent edge controller collects the device running data after the execution of the instruction in real time, and feeds back to the unified intelligent port machine Internet of Things platform, forming a closed-loop management from instruction issuing to execution to data feedback, guaranteeing the accuracy and safety of remote control and management, reducing the cost of on-site manual intervention, and improving the efficiency of port machine device operation and maintenance.

[0098] Further comprising, using an improved particle swarm-gray wolf hybrid algorithm based on target constraints to optimize the energy consumption of the remote control and management operation of the port machine device, and the corresponding calculation formula is as follows:

[0099] In the formula, represents the energy consumption-time delay comprehensive optimization target function; represents the energy consumption weight; represents the time delay weight, ; represents the total energy consumption of the remote control and management operation; represents the number of sub-operations of the remote control and management operation; represents the operation amount of the i-th sub-operation; represents the total time delay of the remote control and management operation; represents the time length of the i-th sub-operation; represents the real-time power of the port machine device; represents the rated power of the port machine device; represents the real-time load rate of the port machine device; represents the real-time speed of the j-th port machine device action; represents the maximum speed of the j-th port machine device action; represents the real-time wind speed of the location of the port machine device; represents the minimum operation amount of the i-th sub-operation.

[0100] The energy consumption weight and the time delay weight are dynamically adjusted according to the port machine operation scene demand. When the port is in the power peak and needs to prioritize the time delay, the energy consumption weight takes a higher value, and the time delay weight takes a lower value. When the operation task urgently needs to guarantee the efficiency, the time delay weight is adjusted upward, and the energy consumption weight is adjusted downward, so as to ensure that the weight distribution is in line with the actual operation priority.

[0101] The number of sub-operations of remote control and management operation is split according to the single complete control flow of the port machine, such as lifting, amplitude changing, rotating and the like. The operation amount of the sub-operation is measured in combination with the equipment operation type, for example, the ton is used as the unit for bulk cargo operation, and the standard box is used as the unit for container operation. The real-time load rate is calculated by the ratio of the real-time power collected by the intelligent edge controller of the port machine to the rated power, reflecting the current load level of the equipment. The real-time speed of the equipment action is obtained by the sensor of the corresponding mechanism in real time, and the maximum speed can be used to judge the action running efficiency. The real-time wind speed data is obtained from the environmental sensor deployed on the port machine equipment, which is used to correct the energy consumption calculation in outdoor operation, for example, the equipment needs to consume additional energy to maintain stability in strong wind environment. The minimum operation amount of the sub-operation is set by referring to the design operation capacity of the port machine equipment and the safety operation specification, so as to avoid the waste of energy consumption caused by too low operation amount. Finally, through the above algorithm, the balance optimization of energy consumption and operation time delay can be realized, and the economy and efficiency of remote control of the port machine can be improved.

[0102] As shown in Figure 2 , it is a system block diagram of a port machine equipment intelligent management system based on Internet of Things provided by an embodiment of the application, the system comprises:

[0103] A data acquisition module is used to acquire multi-dimensional operation monitoring data through the intelligent edge controller of the port machine equipment, including electrical parameters, working condition data and environmental data;

[0104] A data preprocessing module is used to perform protocol normalization and cleaning processing on the multi-dimensional operation monitoring data by the intelligent edge controller, and convert the data into standard Internet of Things data;

[0105] A transmission and storage module is used to transmit and store the standard Internet of Things data to the unified intelligent port machine Internet of Things platform of B / S architecture through optical fiber;

[0106] A report generation module is used to call big data analysis tools and AI models by the unified intelligent port machine Internet of Things platform, perform equipment state analysis, load statistics and potential fault prediction on the standard Internet of Things data, and generate an equipment health report;

[0107] A remote debugging module is used to issue remote debugging instructions to the intelligent edge controller of the port machine by the unified intelligent port machine Internet of Things platform based on the equipment health report, and remotely control and manage the port machine equipment.

[0108] Figure 2 The device of the embodiment can be used to perform the method correspondingly. Figure 1 The steps in the method embodiment have similar principles and technical effects, and thus will not be described here.

[0109] An electronic device includes a memory and a processor, the memory stores a computer program, when the processor runs the computer program stored in the memory, the processor performs the steps of the port machinery equipment intelligent management method based on Internet of Things according to any one of the above.

[0110] As Figure 3 The electronic device 30 includes a processor 31, a memory 32 and a computer program.

[0111] The memory 32 is used for storing the computer program, and the memory can also be a flash memory. The computer program is, for example, an application program, a functional module and the like for implementing the above method.

[0112] The processor 31 is used for executing the computer program stored in the memory to realize each step of the device in the above method. For details, please refer to the related description in the above method embodiment.

[0113] Optionally, the memory 32 can be independent or integrated with the processor 31.

[0114] When the memory 32 is a device independent of the processor 31, the device can further include:

[0115] A bus 33 is used for connecting the memory 32 and the processor 31.

[0116] A readable storage medium, the readable storage medium stores a computer program, the computer program is executed by a processor to realize the steps of the port machinery equipment intelligent management method based on Internet of Things according to any one of the above.

[0117] The readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates transfer of a computer program from one place to another. A computer storage medium can be any available medium that can be accessed by a general purpose or special purpose computer. For example, the readable storage medium can be coupled to the processor, such that the processor can read information from, and write information to, the readable storage medium. Of course, the readable storage medium can be a component of the processor. Accordingly, the processor and the readable storage medium can be considered to be a machine-readable storage medium that can be used to store instructions to perform any one or more of the methods described herein. The machine-readable storage medium can be a non-transitory machine-readable storage medium. Accordingly, any one or more of the methods described herein can be embodied in a non-transitory machine-readable storage medium. The machine-readable storage medium can be a non-transitory machine-readable storage medium. In the above embodiments of the device, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like. The steps of the method disclosed in combination with the present application can be directly embodied in the hardware processor for execution, or be executed by the combination of hardware and software modules in the processor.

[0118] The present application also provides a program product including execution instructions stored in a readable storage medium. At least one processor of the device can read the execution instructions from the readable storage medium, and the at least one processor executes the execution instructions to enable the device to implement the method provided by the various embodiments described above.

[0119] In the above embodiments of the device, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), or the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like. The steps of the method disclosed in combination with the present application can be directly embodied in the hardware processor for execution, or be executed by the combination of hardware and software modules in the processor.

[0120] Through the introduction of the above embodiments, the intelligent port machine edge controller on the port machine equipment collects multi-dimensional operation monitoring data, including electrical parameters, working condition data and environmental data; the intelligent port machine edge controller performs protocol normalization and cleaning processing on the multi-dimensional operation monitoring data, and converts it into standard Internet of Things data; the standard Internet of Things data is transmitted and stored to the unified intelligent port machine Internet of Things platform of B / S architecture through optical fiber; the unified intelligent port machine Internet of Things platform calls big data analysis tools and AI models to analyze the device state, load statistics and potential fault prediction of the standard Internet of Things data, and generates a device health report; based on the device health report, the unified intelligent port machine Internet of Things platform issues remote debugging instructions to the intelligent port machine edge controller to remotely control and manage the port machine equipment, so that the overall intelligent management of the port machine equipment can be realized, potential equipment failures can be identified in a timely manner, the predictive maintenance capability of the equipment is improved, the equipment data island phenomenon is effectively solved, the equipment operation efficiency is significantly improved, and the downtime is reduced.

[0121] The intelligent port machine edge controller is deployed to overcome the disadvantages of isolated port machine equipment data and non-uniform format, improve the data usability and system integration, and perform multi-dimensional collection and protocol normalization processing on the multi-dimensional operation monitoring data. The edge controller has data cleaning capability and can perform real-time processing on abnormal values and missing values. In combination with the optical fiber transmission and offline cache data recovery mechanism, the integrity and time sequence consistency of the data in the transmission process are guaranteed, and the robustness and data reliability of the system are significantly improved. The unified intelligent port machine Internet of Things platform integrates big data analysis tools and AI models to perform multi-dimensional evaluation on the device state, accurately calculate key indicators such as effective utilization rate and performance efficiency of the equipment, perform load statistics on the port machine equipment, identify whether there is overload or insufficient load, and realize early identification and remaining life prediction of potential faults based on historical data and real-time trends, thereby significantly improving the initiative and predictability of equipment maintenance. The unified intelligent port machine Internet of Things platform issues remote debugging instructions according to the device health report to realize precise control and dynamic management of the port machine equipment. By introducing the improved particle swarm-gray wolf hybrid algorithm based on target constraints, the energy consumption is effectively reduced while the work efficiency is ensured, and the overall economy and sustainability of port operations are improved.

[0122] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or make equivalent substitutions for part or all of the technical features; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for intelligent management of port machinery equipment based on the Internet of Things, characterized in that, The method includes: Multi-dimensional operational monitoring data, including electrical parameters, operating condition data, and environmental data, are collected through the port machinery intelligent edge controller on the port machinery equipment. The port machinery intelligent edge controller performs protocol normalization and cleaning on the multi-dimensional operation monitoring data, and converts it into standard Internet of Things data; The standard IoT data is transmitted via optical fiber and stored in a unified smart port machinery IoT platform with a B / S architecture. The unified smart port machinery IoT platform calls big data analysis tools and AI models to perform equipment status analysis, load statistics and potential fault prediction on the standard IoT data, and generate equipment health reports. Based on the equipment health report, the unified smart port machinery IoT platform sends remote debugging instructions to the port machinery intelligent edge controller to remotely control and manage the port machinery equipment; The AI ​​model is deployed on the cloud AI computing cluster of the unified smart port machinery IoT platform, and supports network model conversion based on the TensorFlow framework; The equipment status analysis calculates the equipment status analysis index of the port machinery by performing multi-dimensional statistics on the standard IoT data. The load statistics are calculated by aggregating the standard IoT data to statistically analyze the average load, peak load and load distribution of the port machinery equipment within a unit of time, and to identify whether the port machinery equipment is overloaded or underloaded. The potential fault prediction method learns the changing trends of the standard IoT data, combines it with the historical fault data and wear patterns of the port machinery equipment, identifies potential fault data of the port machinery equipment, and predicts the dynamic maintenance cycle and remaining life of the port machinery equipment. The calculation of the equipment status analysis indicators adopts an improved equipment comprehensive efficiency algorithm based on effective operating time, and the equipment status analysis indicators include the effective utilization rate U of port machinery equipment. eff Effective operating time R of port machinery equipment eff And the performance efficiency coefficient η of port machinery equipment perf The corresponding calculation formula is as follows: In the formula, m represents the number of operating cycles of the port machinery equipment within the statistical period; R i-cycle R represents the total duration of the i-th job cycle; idle R represents the idle standby time of port machinery equipment within the statistical period. down The duration of port machinery downtime due to malfunction within the statistical period is represented by nr; the number of effective operations of the port machinery within the statistical period is represented by R. s G represents the actual duration of the s-th valid operation; s G represents the actual workload of the s-th effective task; s-rated R represents the rated workload of the s-th effective operation; adjust-s pw represents the positioning adjustment time during the s-th effective operation; v represents the number of operating mechanisms of the port machinery; g-nom v represents the rated speed of the g-th operating mechanism; g-act This represents the actual operating speed of the g-th operating mechanism; v avg-nom This represents the average rated speed of all operating mechanisms. This represents the sum of speed deviations of all operating mechanisms; The dynamic maintenance cycle M main and the remaining lifetime M rem The calculation employs a dynamic fuzzy programming algorithm based on remaining lifetime, and the corresponding calculation formula is as follows: In the formula, λ represents the safety redundancy coefficient of the port machinery equipment; γ represents the failure impact coefficient of the port machinery equipment, γ = 0.035; mr represents the number of historical failure types of the port machinery equipment; f i Let f1 represent the severity coefficient of the i-th type of historical fault of the port machinery equipment. When i = 1, f1 represents the severity coefficient of the first type of historical fault of the port machinery equipment, i.e., a minor fault, and f1 = 0.

3. When i = 2, f2 represents the severity coefficient of the second type of historical fault of the port machinery equipment, i.e., a moderate fault, and f2 = 0.

6. When i = 3, f3 represents the severity coefficient of the third type of historical fault of the port machinery equipment, i.e., a severe fault, and f3 = 1.

0. life Indicates the design life of the port machinery equipment; M used Indicates the usage time of the port machinery equipment; μ j μ1 represents the j-th remaining life correction factor of the port machinery equipment. When j=1, μ1 represents the first remaining life correction factor of the port machinery equipment, which is the failure frequency correction factor. When j=2, μ2 represents the second remaining life correction factor of the port machinery equipment, which is the overload duration correction factor. When j=3, μ3 represents the third remaining life correction factor of the port machinery equipment, which is the maintenance quality correction factor. N represents the product of the remaining life correction factors for port machinery equipment; fault Indicates the historical number of failures of the port machinery equipment; N total Indicates the historical number of operations performed by the port machinery equipment; M overload Indicates the historical overload operating time of the port machinery equipment; M total Indicates the total historical operating time of the port machinery equipment; M qual Indicates the historical qualified maintenance duration of port machinery equipment; M ' total This indicates the total historical interval for maintenance of port machinery equipment.

2. The intelligent management method for port machinery equipment based on the Internet of Things according to claim 1, characterized in that, The electrical parameters include the circuit breaker status, contactor status, and inverter operating parameters of the port machinery equipment; the operating data includes the mechanical position, operating time, and workload data of the port machinery equipment; the environmental data includes the real-time wind speed and real-time temperature at the location of the port machinery equipment. Specifically, a dynamic correction algorithm based on multi-source error compensation is used to correct the workload data in real time, and the corrected workload data Q is... corr as follows: ξ1=1-0.042sin(α)+0.018cos(β) In the formula, Q raw This indicates the workload data of the port machinery equipment before correction; ξ p This represents the p-th multi-source error compensation coefficient of the port machinery equipment; Δδ represents the product of all multi-source error compensation coefficients; Δδ represents the aging correction amount of the port machinery equipment. R used Indicates the usage time of the port machinery equipment, R life ξ1 represents the design life of the port machinery equipment; α represents the amplitude angle of the luffing mechanism; β represents the yaw angle of the rotating mechanism; ξ2 represents the wind speed compensation coefficient of the port machinery equipment; exp() represents an exponential function with the natural constant e as its base; v e Indicates the real-time wind speed at the location of the port machinery equipment; ξ3 represents the ambient temperature compensation coefficient; TEM env Indicates real-time temperature; TEM std Indicates standard temperature; ξ4 represents the power supply voltage compensation coefficient; P supply Indicates real-time power supply; P nom This indicates the rated power supply.

3. The intelligent management method for port machinery equipment based on the Internet of Things according to claim 1, characterized in that, The port machinery intelligent edge controller performs protocol normalization and cleaning on the multi-dimensional operation monitoring data, and converts it into standard IoT data, specifically including: The multi-protocol communication bus interface of the port machinery intelligent edge controller is used to perform protocol normalization processing on the multi-dimensional operation monitoring data; The multi-dimensional operation monitoring data is cleaned by removing outliers, filling in missing values, and reducing noise. The multi-dimensional operational monitoring data, after protocol normalization and cleaning, is converted into the standard IoT data.

4. The intelligent management method for port machinery equipment based on the Internet of Things according to claim 1, characterized in that, During the process of transmitting the standard IoT data to the unified smart port machinery IoT platform with B / S architecture via optical fiber, a local caching mechanism is activated when the network is interrupted to store the standard IoT data in an orderly manner according to the timestamp. After the network is reconnected, the offline cache data recovery mechanism is automatically triggered. Based on the aforementioned network outage cached data recovery mechanism, the cached standard IoT data is subjected to integrity verification, including verifying the continuity of timestamps and verifying data integrity through hash values. After the verification is passed, the cached standard IoT data is uploaded using a dual-priority transmission algorithm based on time priority and data importance. The calculation formula for the transmission level of the cached standard IoT data d is as follows: In the formula, Pri(d) represents the transmission level of the cached standard IoT data d; ω o This represents the time priority weight of cached standard IoT data; ω i The data importance weight represents the cached standard IoT data, and ω o +ω i =1; T d T0 represents the storage timestamp of the cached standard IoT data d; T0 represents the network connection timestamp. I(d) represents the data importance score of the cached standard IoT data d; ω k This represents the data importance score weight of the k-th sub-criteria IoT data in the cache; I k (d) represents the data importance score of the kth sub-standard IoT data in the cache. When k=1, I1(d) represents the data importance score of the first sub-standard IoT data in the cache, namely the operational fault data of the port machinery equipment. When k=2, I2(d) represents the data importance score of the second sub-standard IoT data in the cache, namely the key operating condition data of the port machinery equipment. When k=3, I3(d) represents the data importance score of the third sub-standard IoT data in the cache, namely the real-time environmental data of the location of the port machinery equipment.

5. The intelligent management method for port machinery equipment based on the Internet of Things according to claim 1, characterized in that, It also includes using an improved particle swarm optimization-gray wolf hybrid algorithm based on objective constraints to optimize energy consumption for remote control and management operations of the port machinery equipment. The corresponding calculation formula is as follows: s.t.A≤A rated ×(1.15-0.25θ) B i ≥B i-min In the formula, F represents the energy consumption-delay integrated optimization objective function; w1 represents the energy consumption weight; w2 represents the delay weight, w1+w2=1; E total The total energy consumption of remote control and management operations is represented by irr; the number of sub-operations in the remote control and management operations is represented by .B i Z represents the workload of the i-th sub-task; delay Indicates the total latency of remote control and management operations; c i A represents the duration of the i-th sub-operation; A represents the real-time power of the port machinery; A rated θ represents the rated power of the port machinery; θ represents the real-time load rate of the port machinery; v j This represents the real-time speed of the j-th port machinery unit; v j-max v represents the maximum operating speed of the j-th port machinery unit; e Indicates the real-time wind speed at the location of the port machinery equipment; B i-min This represents the minimum workload of the i-th sub-task.

6. An IoT-based intelligent management system for port machinery equipment, applied to the IoT-based intelligent management method for port machinery equipment as described in any one of claims 1-5, characterized in that, The system includes: The data acquisition module is used to collect multi-dimensional operation monitoring data through the port machinery intelligent edge controller on the port machinery equipment, including electrical parameters, operating condition data and environmental data; The data preprocessing module is used by the port machinery intelligent edge controller to perform protocol normalization and cleaning on the multi-dimensional operation monitoring data, and convert it into standard Internet of Things data. The transmission and storage module is used to transmit the standard IoT data via optical fiber and store it in a unified smart port machinery IoT platform with a B / S architecture. The report generation module is used by the unified smart port machinery IoT platform to call big data analysis tools and AI models to perform equipment status analysis, load statistics and potential fault prediction on the standard IoT data, and generate equipment health reports. The remote debugging module is used to send remote debugging commands from the unified smart port machinery IoT platform to the port machinery intelligent edge controller based on the equipment health report, so as to remotely control and manage the port machinery equipment.

Images