A production control method and system for automated container terminal

Abstract

The present invention discloses a production control method and system for an automated container terminal, and specifically relates to the technical field of production equipment control, comprising the following steps: using a sensor to capture vibration information of automated container terminal equipment in real time at an initial sampling frequency, extracting vibration frequency characteristic data after preprocessing and performing preliminary analysis to determine whether there are potential hidden dangers of failure, and for equipment with hidden dangers, obtaining operation information, generating a power quality index and a sound quality index, and generating a production quality coefficient through a machine learning model, and according to the production quality coefficient, dividing the equipment into high risk and low risk, and performing early warning and intelligent regulation respectively; the present invention can reduce the number of unplanned shutdowns of equipment, avoid excessive use of equipment, and extend the service life of equipment, and reduce maintenance costs and data processing costs through real-time monitoring and intelligent regulation of the operating status of production equipment, while improving the operating efficiency and stability of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of production equipment control, and more specifically, to a production control method and system for an automated container terminal. Background Art

[0002] Automated container terminal production control refers to the intelligent control and optimization of various production operations and management processes of container terminals through automation technology and information systems. Its purpose is to improve the terminal's operating efficiency, reduce labor costs, enhance safety, and improve the overall control and management level. These technologies include automated equipment such as automatic guided vehicles (AGVs) and automated stacking cranes (ASCs) that work together to ensure the efficient operation of terminal production operations.

[0003] The existing technology has the following shortcomings: the production control of automated container terminals covers all aspects from ship berthing, container loading and unloading, yard management to landside container collection, realizing unmanned or less-manned operation, and therefore involves the management of various production equipment of automated container terminals. The reliability and stability of automated equipment and systems are key. Any equipment failure will lead to interruption of terminal control and affect production efficiency and service quality, especially in high-intensity operating environments. Equipment maintenance and troubleshooting are particularly important. Therefore, a production control method and system for automated container terminals are proposed herein. Summary of the invention

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An automated container terminal production control method comprises the following steps:

[0006] The sensor is used to capture the vibration information of various production equipment of the automated container terminal in real time at the initial sampling frequency, and the vibration information is pre-processed. Then, the vibration frequency characteristic data is extracted and preliminarily analyzed to determine whether there are potential faults in the various production equipment of the automated container terminal.

[0007] The operation information of production equipment with potential failure hazards is obtained, and then abnormal analysis is performed to generate a power quality index and a sound quality index. The power quality index and the sound quality index are then transmitted to a pre-trained machine learning model, and a production quality coefficient is generated through the pre-trained machine learning model.

[0008] Based on the generated production quality coefficient, the production equipment with potential failure hazards is divided into high-risk production equipment and low-risk production equipment;

[0009] For high-risk production equipment, different levels of early warning signals are issued based on the production quality coefficient. For low-risk production equipment, its maintenance frequency is intelligently regulated. For production equipment that does not have potential failure hazards, its actual sampling frequency is intelligently regulated based on the initial sampling frequency.

[0010] In a preferred embodiment, the steps of determining whether various production equipment of the automated container terminal has potential failure hazards are as follows:

[0011] For the target production equipment, the extracted vibration frequency characteristic data is obtained to obtain the vibration frequency characteristic sequence P: ; n is the total number of feature data extracted, then the vibration frequency average value and vibration frequency standard deviation of the vibration frequency feature sequence P are calculated, and the vibration frequency average value and vibration frequency standard deviation are compared with the preset fluctuation reference range and fluctuation reference threshold respectively. If the vibration frequency average value is within the preset fluctuation reference range and the vibration frequency standard deviation is less than or equal to the fluctuation reference threshold, a normal signal is generated. If the vibration frequency average value is not within the preset fluctuation reference range and the vibration frequency standard deviation is less than or equal to the fluctuation reference threshold, a hidden danger signal is generated. When the hidden danger signal is generated, it indicates that the target production operation equipment has a hidden danger of potential failure.

[0012] In a preferred embodiment, when performing abnormality analysis, power characteristics and acoustic characteristics are respectively extracted from the operation information of the production operation equipment with potential failure hazards.

[0013] In a preferred embodiment, the logic for obtaining the power quality index is:

[0014] Obtain the instantaneous power data P(t) of the production equipment during operation. The sampling time interval is Δt, and the total number of sampling points is N. First, calculate the instantaneous power standard deviation and the instantaneous power average, and then calculate the power fluctuation value at each time point. The calculation formula is: ; Indicates at time The power fluctuation value, represents the instantaneous average power, Indicates at time The power value is then converted into the frequency domain using the fast Fourier transform to obtain the frequency component of the power P(f). The transformation formula is: ; P(f) represents the power value at frequency f, and then the total harmonic distortion is calculated as follows: ;THD stands for total harmonic distortion, represents the amplitude of the fundamental wave, Represents the amplitude of the k-th order harmonic and calculates the power factor. The formula is: ; PF stands for power factor, Represents the phase difference between voltage and current and is calculated as: ; is the voltage time series, and finally generates the power quality index. The power quality index calculation formula is: ; represents the instantaneous power standard deviation, and PQI represents the power quality index.

[0015] In a preferred embodiment, the logic for obtaining the sound quality index is:

[0016] The sound signal X(t) of the production equipment during operation is obtained. The sampling time interval is Δt, the total number of sampling points is N, and the time series is converted to the frequency domain to obtain the time-frequency spectrum X(t,f). The conversion formula is: ; represents a discrete time series, f is the frequency, Represents the time window function, and then calculates the spectrum average in each time window , and the standard deviation of the spectrum , then calculate the smoothness of the spectrum, the calculation formula is: ; T is the total number of time windows, Indicates the smoothness of the spectrum;

[0017] Calculate the spectrum entropy using the formula: ; represents the normalized power spectral density of the spectrum at time t and frequency f, C is a constant, represents spectral entropy;

[0018] Calculate the spectrum centroid using the formula: ; represents the centroid of the spectrum at frequency f;

[0019] Calculate the sound quality index using the following formula: ; F is the total frequency number, SQI stands for sound quality index.

[0020] In a preferred embodiment, based on the generated production quality coefficient, the production operation equipment with potential failure hazards is divided into high-risk production operation equipment and low-risk production operation equipment respectively, which means:

[0021] The generated production quality coefficient is compared with the preset production safety reference coefficient. If the generated production quality coefficient is greater than or equal to the preset production safety reference coefficient, the production operation equipment with potential failure hazards will be classified as low-risk production operation equipment. If the generated production quality coefficient is less than the preset production safety reference coefficient, the production operation equipment with potential failure hazards will be classified as high-risk production operation equipment.

[0022] For high-risk production equipment, different levels of early warning signals are issued based on the production quality coefficient:

[0023] The production quality coefficient of high-risk production equipment and the preset safety benchmark value are obtained, and the ratio of the production quality coefficient to the preset safety benchmark value is calculated. A warning interval-level form is preset, and the level corresponding to the warning interval into which the ratio of the production quality coefficient to the preset safety benchmark value falls is used as the level of the warning signal.

[0024] In a preferred embodiment, for low-risk production equipment, intelligently regulating the maintenance frequency thereof refers to:

[0025] Get the preset standard maintenance time interval for low-risk production operation equipment, and then calculate the adjusted maintenance time interval: ; BSi is the standard maintenance time interval corresponding to the production equipment numbered i, k is the preset adjustment coefficient, PQC is the production quality coefficient, and M is the maintenance time interval after adjustment.

[0026] In a preferred embodiment, for production operation equipment without hidden dangers of potential failure, intelligently controlling its actual sampling frequency based on the initial sampling frequency means:

[0027] Get the initial sampling frequency and the time interval between the production equipment without potential failure and the last time it was judged to have potential failure, and then substitute it into the control formula: ; Y is the sampling frequency after adjustment, R is a constant, v is the preset adjustment coefficient, Ti is the time interval, and when the production equipment is sampled for the first time, before the production equipment that is judged to have potential faults appears, Ti takes the preset maximum time value.

[0028] In a preferred embodiment, an automated container terminal production control system includes an information collection module, a preliminary judgment module, an abnormality analysis module, a classification module, and an early warning and control module;

[0029] The information collection module is used to use sensors to capture the vibration information of various production equipment of the automated container terminal in real time at the initial sampling frequency;

[0030] Preliminary judgment is used to pre-process the vibration information, then extract the vibration frequency characteristic data and conduct preliminary analysis to determine whether there are potential failure hazards in various production equipment of the automated container terminal;

[0031] The abnormality analysis module is used to obtain operation information of production equipment with potential failure hazards, and then perform abnormality analysis to generate a power quality index and a sound quality index. The power quality index and the sound quality index are then transmitted to a pre-trained machine learning model to generate a production quality coefficient through the pre-trained machine learning model.

[0032] The classification module is used to classify the production operation equipment with potential failure hazards into high-risk production operation equipment and low-risk production operation equipment based on the generated production quality coefficient;

[0033] The early warning and control module includes an early warning unit, a maintenance control unit and a sampling control unit. The early warning unit is used to issue early warning signals of different levels based on the production quality coefficient for high-risk production equipment; the maintenance control unit is used to perform intelligent control of the maintenance frequency of low-risk production equipment; the sampling control unit is used to perform intelligent control of the actual sampling frequency of production equipment that does not have potential faults based on the initial sampling frequency.

[0034] Technical effects and advantages of the present invention:

[0035] The present invention can timely discover potential hidden dangers of equipment failures by calculating the production quality coefficient and continuously monitoring it. Different levels of early warning signals are issued for high-risk equipment to ensure that preventive measures are taken before potential failures occur, thereby significantly improving the safety and reliability of the equipment; for low-risk production equipment, the maintenance frequency is intelligently regulated, and the maintenance time interval is dynamically adjusted according to the actual operating status, effectively avoiding excessive maintenance and delayed maintenance, optimizing the allocation of maintenance resources, and improving the economy and efficiency of maintenance work; for production equipment without potential hidden dangers of failures, the sampling frequency is intelligently regulated, and the sampling frequency is reasonably adjusted according to the real-time status and historical records of the equipment operation, ensuring that high-frequency sampling is maintained at critical moments, and the sampling frequency is reduced during stable operation, thereby efficiently managing the operating status of the equipment and saving data collection and processing costs.

[0036] The present invention reduces the number of unplanned downtimes of equipment and avoids excessive use of equipment through accurate fault warnings and optimized maintenance strategies, thereby extending the service life of equipment and reducing the overall use cost of equipment. Through real-time monitoring and intelligent regulation of the operating status of production equipment, the present invention ensures that the equipment operates in the best condition, reduces downtime due to faults, and improves production efficiency and product quality. Through intelligent maintenance and sampling regulation, maintenance costs and data processing costs are reduced, while the operating efficiency and stability of the equipment are improved, thereby comprehensively reducing management and control costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0038] Figure 1 This is a schematic diagram of an automated container terminal production control method in the present invention.

[0039] Figure 2 It is a schematic diagram of an automated container terminal production control system in the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Reference Figure 1 - Figure 2 The following embodiments are obtained:

[0042] Embodiment 1: A method for production control of an automated container terminal, comprising the following steps:

[0043] The vibration information of various production equipment of the automated container terminal is captured in real time by using the sensor at the initial sampling frequency, and the vibration information is preprocessed, and then the vibration frequency characteristic data is extracted and preliminarily analyzed to determine whether the various production equipment of the automated container terminal has potential failure hazards; the preprocessing operation includes using a low-pass filter to remove high-frequency noise, standardizing the vibration data, and ensuring the information quality to facilitate subsequent analysis operations. The specific method of the preprocessing operation is the existing technology, and the specific process of the preprocessing operation is:

[0044] Data collection: Sensors are used to capture the vibration information of various production equipment in automated container terminals in real time at the initial sampling frequency. This information is usually recorded in the form of a time series, with each data point corresponding to a timestamp and vibration intensity value.

[0045] Data cleaning: De-noising: Remove high-frequency noise by using filters (such as low-pass filters), retain useful vibration information, and eliminate high-frequency interference caused by sensors or the environment.

[0046] Missing value processing: Check whether there are missing values ​​in the data. If there are missing values, interpolation or mean filling method can be used to handle the missing data.

[0047] Outlier detection: Identify and handle outliers (such as excessively high or low vibration values) that may be caused by equipment failure or sensor failure. These outliers can be replaced with the mean or median.

[0048] Data normalization: Normalize the vibration information and scale the data to the same range (such as 0 to 1 or -1 to 1) to eliminate the impact of data differences from different devices or different time periods on subsequent analysis.

[0049] Feature extraction: Vibration frequency feature extraction: Extract vibration frequency features from preprocessed vibration data, such as peak frequency, average frequency, frequency standard deviation, etc. These features can reflect the vibration pattern and health status of the equipment.

[0050] Data segmentation: Data is segmented according to different stages or time intervals of equipment operation for further analysis. This helps to identify changes in equipment operation status within different time periods.

[0051] The operation information of production equipment with potential failure hazards is obtained, and then abnormal analysis is performed to generate a power quality index and a sound quality index. The power quality index and the sound quality index are then transmitted to a pre-trained machine learning model, and a production quality coefficient is generated through the pre-trained machine learning model.

[0052] Based on the generated production quality coefficient, the production equipment with potential failure hazards is divided into high-risk production equipment and low-risk production equipment;

[0053] For high-risk production equipment, different levels of early warning signals are issued based on the production quality coefficient. For low-risk production equipment, its maintenance frequency is intelligently regulated. For production equipment that does not have potential failure hazards, its actual sampling frequency is intelligently regulated based on the initial sampling frequency.

[0054] The steps for determining whether various production equipment of the automated container terminal have potential fault hazards are as follows: For the target production equipment, the extracted vibration frequency characteristic data is obtained to obtain the vibration frequency characteristic sequence P: ; n is the total number of feature data extracted, then the vibration frequency average value and vibration frequency standard deviation of the vibration frequency feature sequence P are calculated, and the vibration frequency average value and vibration frequency standard deviation are compared with the preset fluctuation reference range and fluctuation reference threshold respectively. If the vibration frequency average value is within the preset fluctuation reference range and the vibration frequency standard deviation is less than or equal to the fluctuation reference threshold, a normal signal is generated. If the vibration frequency average value is not within the preset fluctuation reference range and the vibration frequency standard deviation is less than or equal to the fluctuation reference threshold, a hidden danger signal is generated. When the hidden danger signal is generated, it indicates that the target production operation equipment has a hidden danger of potential failure.

[0055] The vibration frequency fluctuation of the equipment will have a significant impact on the operation quality and safety of the equipment. Large vibration frequency fluctuations may indicate wear, looseness or imbalance of the internal parts of the equipment, which will not only lead to a decrease in the operating efficiency of the equipment, but also increase energy consumption and shorten the life of the equipment. At the same time, frequent or severe vibration fluctuations may cause fatigue damage to the structural parts, increase the risk of equipment failure, and in severe cases may even lead to sudden failures or safety accidents of the equipment. In addition, vibration frequency fluctuations will also affect the operating environment and personnel safety. Excessive vibration may cause an increase in noise in the environment around the equipment, affect the operator's work comfort and concentration, and thus affect production efficiency and work safety. Therefore, monitoring the vibration frequency fluctuation of the equipment is a key indicator for judging the stable operation and safe production of the equipment. In addition, through a systematic and automated way, it is possible to judge whether there are potential fault hazards in the production equipment of the automated container terminal. By obtaining and analyzing the vibration frequency characteristic data of the equipment, calculating its average value and standard deviation, and comparing it with the preset reference range and threshold, it is easy to implement and can achieve continuous monitoring. It can effectively monitor the operating status of the equipment, timely discover abnormal fluctuations in the operation of the equipment, and help prevent and reduce equipment failures, thereby improving the reliability and service life of the equipment. By monitoring and identifying potential equipment failure hazards and performing preventive maintenance or repairs in a timely manner, production accidents caused by equipment failure can be reduced and the safety of production operations can be ensured.

[0056] When performing abnormality analysis, power characteristics and acoustic characteristics are extracted from the operation information of the production operation equipment with potential failure hazards, and the operation information includes but is not limited to power characteristics and acoustic characteristics.

[0057] The power quality index PQI is used to evaluate and measure the power quality of equipment. Through PQI, we can understand the power quality of equipment. The larger the PQI is, the higher the power quality of the equipment is, the more stable the power is, the smaller the harmonic distortion is, the higher the power factor is, the equipment is in good operating condition, the lower the risk is, the higher the energy utilization efficiency is, the lower the power loss is, and due to the reduced equipment wear and loss, the maintenance and replacement frequency is low, and the cost is low. The smaller the PQI is, the lower the power quality of the equipment is, the larger the power fluctuation is, the larger the harmonic distortion is, the lower the power factor is, the poorer the equipment is, the higher the potential risk is, and the more prone to failure is, the lower the energy utilization efficiency is, the higher the power loss is, and due to the increased equipment wear and loss, the maintenance and replacement frequency is high, the cost is high, the power system is unstable, and the failure rate is high, which may cause system shutdown or production interruption. The logic for obtaining the power quality index is: obtain the instantaneous power data P(t) of the production equipment during operation, the sampling time interval is Δt, the total number of sampling points is N, first calculate the instantaneous power standard deviation and the instantaneous power average, and then calculate the power fluctuation value at each time point. The calculation formula is: ; Indicates at time The power fluctuation value reflects the difference between the power at each time point and the average power. The larger the fluctuation value, the more drastic the power change. Indicates the instantaneous power average value, reflecting the basic operating power level of the equipment. Indicates at time The power value is then converted into the frequency domain using the fast Fourier transform to obtain the power values ​​of different frequency components, which helps analyze the frequency characteristics of the power and obtain the frequency component P(f) of the power. The transformation formula is: ; P(f) represents the power value at frequency f, j is the imaginary unit, N is the total number of sampling points, P(t) represents the power value in the time series, and then calculate the total harmonic distortion, the formula is: ; THD stands for total harmonic distortion, which reflects the influence of harmonic components in the power of the equipment. The larger the THD, the more serious the harmonic distortion, indicating that the power quality is worse. represents the amplitude of the fundamental wave, Represents the amplitude of the k-th order harmonic and calculates the power factor. The formula is: ; The power factor PF indicates the phase relationship between voltage and current. The higher the power factor, the higher the power utilization efficiency of the equipment. Indicates the phase difference between voltage and current, reflecting the effectiveness of power transmission. The smaller the phase difference, the higher the power factor. The calculation formula is: ; is the voltage time series, specifically at time The voltage value is N, and the total number of sampling points is used to generate the power quality index. The power quality index calculation formula is: ; It represents the instantaneous power standard deviation, indicating the degree of fluctuation of equipment power. The larger the standard deviation, the more obvious the power fluctuation. PQI stands for power quality index.

[0058] The logic for obtaining the sound quality index is:

[0059] The sound signal X(t) of the production equipment during operation is obtained. The sampling time interval is Δt, the total number of sampling points is N, and the time series is converted to the frequency domain to obtain the time-frequency spectrum X(t,f). The conversion formula is: ; represents a discrete time series, f is the frequency, Represents the time window function, and then calculates the spectrum average in each time window , and the standard deviation of the spectrum , and then calculate the smoothness of the spectrum, the calculation formula is: ; T is the total number of time windows, Indicates the smoothness of the spectrum, which means the smoothness of the change of the spectrum between adjacent time windows at frequency f;

[0060] Calculate the spectrum entropy using the formula: ; represents the normalized power spectral density of the spectrum at time t and frequency f, C is a constant, It represents the spectrum entropy. In the calculation of spectrum entropy H(f), the base of the log function is usually 2, which is used to calculate the logarithm with base 2, which is consistent with the unit "bit" commonly used in information entropy calculation. T is the total number of time windows. The normalized power spectrum density formula is: ;

[0061] Calculate the spectrum centroid using the formula: ; represents the centroid of the spectrum at frequency f, and T is the total number of time windows; It indicates the center of gravity of the spectrum at frequency f, which is usually related to the "brightness" of the sound. The sound quality index is calculated using the formula: ; F is the total number of frequencies, SQI represents the sound quality index, and the larger the SQI is, the higher the sound quality of the equipment when it is running, the sound is stable and uniform, the spectrum is smooth, the randomness is low, and the spectrum centroid is reasonable. The equipment is in good operating condition: the sound is stable, and the vibration and noise are small. Comfortable operating environment: equipment with high sound quality has low operating noise and little impact on operators. Low maintenance cost: due to the high sound quality, the equipment may be in a good mechanical condition, reducing the maintenance frequency and cost. Small SQI: the sound quality of the equipment when it is running is low, the sound fluctuates greatly, the spectrum smoothness is low, the randomness is high, and the spectrum centroid is unreasonable. The equipment is in poor operating condition: the sound is unstable, and there may be large vibration and noise. Poor operating environment: the noise is loud, affecting the working environment and efficiency of the operator. High maintenance cost: low sound quality may indicate that the mechanical condition of the equipment is poor, requiring more frequent maintenance and inspection.

[0062] The machine learning model is not specifically limited here, and any model that can perform comprehensive analysis on the power quality index and the sound quality index to generate a production quality coefficient is acceptable. In order to implement the technical solution of the present invention, the present invention provides a specific implementation method: the power quality index and the sound quality index are adjusted so that their data ranges are within the same scale, and then substituted into a pre-trained machine learning model, such as: POQ is the production quality coefficient, k1 and k2 are preset proportional coefficients used to adjust the degree of influence of parameters on the results. is the sound quality index after normalization. It is the power quality index after normalization. The larger the production quality coefficient is, the better the safety and stability of the production equipment is. The selection basis of the preset proportional coefficient is:

[0063] Device characteristics: Different devices have different sensitivities to power quality and sound quality. Therefore, when selecting the proportionality coefficients k1 and k2, the device's response and importance to these two indicators should be considered. For example, some devices may pay more attention to power quality, so k1 can be given a higher weight.

[0064] Safety requirements: In a production environment, some devices have very high requirements for safety and stability. In this case, a higher proportionality factor may be required to strictly control and monitor the status of the device.

[0065] Data statistics and analysis: By conducting statistical analysis on historical data, we can observe the impact of the power quality index and sound quality index on the operating status of the equipment, and thus determine a reasonable proportional coefficient.

[0066] Expert experience: The experience and suggestions of industry experts and equipment manufacturers are also important references for setting the scale factor. They can determine a reasonable scale factor based on the experience of using the equipment.

[0067] Based on the generated production quality coefficient, the production equipment with potential failure hazards is divided into high-risk production equipment and low-risk production equipment, which means:

[0068] The generated production quality coefficient is compared with the preset production safety reference coefficient. If the generated production quality coefficient is greater than or equal to the preset production safety reference coefficient, the production equipment with potential failure hazards will be divided into low-risk production equipment. If the generated production quality coefficient is less than the preset production safety reference coefficient, the production equipment with potential failure hazards will be divided into high-risk production equipment. The production safety reference coefficient is a pre-set threshold value used to measure the safety and reliability of the equipment. The coefficient can be set based on historical data, industry standards and expert opinions. Through the division operation, the risk probability of the production equipment can be effectively judged based on the operating status of the equipment and the production quality coefficient, which is conducive to the subsequent adoption of different control strategies and early warning strategies.

[0069] For high-risk production equipment, different levels of early warning signals are issued based on the production quality coefficient:

[0070] The production quality coefficient of high-risk production equipment and the preset safety reference value are obtained, and the ratio of the production quality coefficient to the preset safety reference value is calculated. A warning interval-level form is preset, and the level corresponding to the warning interval in which the ratio of the production quality coefficient to the preset safety reference value falls is used as the level of the warning signal. Through the preset warning interval-level form, the ratio can be mapped to different warning levels, and the corresponding level of warning signal is issued according to the interval in which the ratio falls. This can effectively monitor the operating status of high-risk production equipment, and timely issue warning signals of different levels according to the ratio of the production quality coefficient to the safety reference value. This helps to identify potential fault hazards in advance and take corresponding management measures to ensure the safety and reliability of the production process.

[0071] For low-risk production equipment, intelligent control of maintenance frequency means:

[0072] Get the preset standard maintenance time interval for low-risk production operation equipment, and then calculate the adjusted maintenance time interval: ; BSi is the standard maintenance time interval corresponding to the production operation equipment numbered i, k is the preset adjustment coefficient, which is used to adjust the preset coefficient of the maintenance time interval, usually a positive number, used to adjust the maintenance frequency, and the basis for the value of k can be the risk assessment of the equipment: for low-risk equipment, k can be set to a smaller value, because these equipment usually operate under relatively stable conditions and do not require frequent maintenance. Equipment with higher risks may require a higher k value to ensure timely maintenance and overhaul. PQC is the production quality coefficient, which is generated by the pre-trained machine learning model to reflect the current quality status of the equipment. M is the maintenance time interval after regulation. Through this intelligent maintenance frequency regulation method, the maintenance time interval can be dynamically adjusted according to the actual operation quality of the equipment, thereby achieving the following goals: Optimize maintenance resources: avoid excessive maintenance or delayed maintenance, and improve the efficiency and economy of maintenance work; extend equipment life: optimize the maintenance frequency while ensuring the reliability of the equipment, which helps to extend the service life of the equipment; improve equipment reliability: adjust the maintenance interval according to the actual status of the equipment, which helps to timely discover and deal with potential problems and improve the overall reliability of the equipment; reduce maintenance costs: by optimizing the maintenance frequency, unnecessary maintenance operations can be reduced and maintenance costs can be reduced.

[0073] For production equipment without potential failure hazards, intelligent control of the actual sampling frequency based on the initial sampling frequency means:

[0074] Get the initial sampling frequency and the time interval between the production equipment without potential failure and the last time it was judged to have potential failure, and then substitute it into the control formula: ; Y is the sampling frequency after adjustment, R is a constant, v is the preset adjustment coefficient, Ti is the time interval. When the production equipment is sampled for the first time, before the production equipment that is judged to have potential faults appears, in order to avoid infinite values ​​after adjustment, for practical reasons, Ti is taken as the preset maximum time value. Through this intelligent sampling frequency control method, the sampling frequency can be dynamically adjusted according to the actual status and historical records of the equipment, so as to achieve the following goals: Optimize data acquisition resources: avoid unnecessary high-frequency sampling, reduce the burden of data processing and storage, and improve the efficiency of data acquisition; improve sampling efficiency: reduce the sampling frequency when the equipment is running stably, and increase the sampling frequency when close monitoring is required to ensure the effectiveness of data acquisition; extend equipment life: reduce the potential impact of frequent sampling on the equipment and extend the service life of the equipment; reduce operation and maintenance costs: by optimizing the sampling frequency, reduce the cost of data acquisition and processing, and improve the overall operation and maintenance efficiency.

[0075] Embodiment 2: An automated container terminal production control system, comprising an information collection module, a preliminary judgment module, an abnormality analysis module, a classification module, and an early warning and control module;

[0076] The information collection module is used to use sensors to capture the vibration information of various production equipment of the automated container terminal in real time at the initial sampling frequency;

[0077] Preliminary judgment is used to pre-process the vibration information, then extract the vibration frequency characteristic data and conduct preliminary analysis to determine whether there are potential failure hazards in various production equipment of the automated container terminal;

[0078] The abnormality analysis module is used to obtain operation information of production equipment with potential failure hazards, and then perform abnormality analysis to generate a power quality index and a sound quality index. The power quality index and the sound quality index are then transmitted to a pre-trained machine learning model to generate a production quality coefficient through the pre-trained machine learning model.

[0079] The classification module is used to classify the production operation equipment with potential failure hazards into high-risk production operation equipment and low-risk production operation equipment based on the generated production quality coefficient;

[0080] The early warning and control module includes an early warning unit, a maintenance control unit and a sampling control unit. The early warning unit is used to issue early warning signals of different levels based on the production quality coefficient for high-risk production equipment; the maintenance control unit is used to perform intelligent control of the maintenance frequency of low-risk production equipment; the sampling control unit is used to perform intelligent control of the actual sampling frequency of production equipment that does not have potential faults based on the initial sampling frequency.

[0081] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0082] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0083] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0085] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A production control method for an automated container terminal. It is characterized in that The following steps are involved: The sensor is used to capture the vibration information of various production equipment of the automated container terminal in real time at the initial sampling frequency, and the vibration information is pre-processed. Then, the vibration frequency characteristic data is extracted and preliminarily analyzed to determine whether there are potential failure hazards in the various production equipment of the automated container terminal. The operation information of production equipment with potential failure hazards is obtained, and then abnormal analysis is performed to generate a power quality index and a sound quality index. The power quality index and the sound quality index are then transmitted to a pre-trained machine learning model, and a production quality coefficient is generated through the pre-trained machine learning model. Based on the generated production quality coefficient, the production equipment with potential failure hazards is divided into high-risk production equipment and low-risk production equipment; For high-risk production equipment, different levels of early warning signals are issued based on the production quality coefficient. For low-risk production equipment, its maintenance frequency is intelligently regulated. For production equipment without potential failure hazards, its actual sampling frequency is intelligently regulated based on the initial sampling frequency. The steps to determine whether the various production equipment of the automated container terminal has potential failure hazards are as follows: For the target production equipment, the extracted vibration frequency characteristic data is obtained to obtain the vibration frequency characteristic sequence P: ; n is the total number of feature data extracted, then the vibration frequency average value and the vibration frequency standard deviation of the vibration frequency feature sequence P are calculated, and the vibration frequency average value and the vibration frequency standard deviation are compared with the preset fluctuation reference range and the fluctuation reference threshold value respectively. If the vibration frequency average value is within the preset fluctuation reference range and the vibration frequency standard deviation is less than or equal to the fluctuation reference threshold value, a normal signal is generated. If the vibration frequency average value is within the preset fluctuation reference range and the vibration frequency standard deviation is less than or equal to the fluctuation reference threshold value, a hidden danger signal is generated. When the hidden danger signal is generated, it indicates that the target production operation equipment has a hidden danger of potential failure; When performing abnormal analysis, power characteristics and acoustic characteristics are extracted from the operation information of production equipment with potential failure hazards; The logic for obtaining the power quality index is: Obtain the instantaneous power data P(t) of the production equipment during operation. The sampling time interval is Δt, and the total number of sampling points is N. First, calculate the instantaneous power standard deviation and the instantaneous power average, and then calculate the power fluctuation value at each time point. The calculation formula is: ; Indicates at time The power fluctuation value, represents the instantaneous average power, Indicates at time The power value is then converted into the frequency domain using the fast Fourier transform to obtain the frequency component P(f) of the power. The transformation formula is: ; P(f) represents the power value at frequency f, and then the total harmonic distortion is calculated as follows: ; THD stands for Total Harmonic Distortion. represents the amplitude of the fundamental wave, Represents the amplitude of the k-th order harmonic and calculates the power factor. The formula is: ; PF stands for power factor, Represents the phase difference between voltage and current and is calculated as: ; is the voltage time series, and finally generates the power quality index. The power quality index calculation formula is: ; represents the instantaneous power standard deviation, and PQI represents the power quality index; The logic for obtaining the sound quality index is: The sound signal X(t) of the production equipment during operation is obtained. The sampling time interval is Δt, the total number of sampling points is N, and the time series is converted to the frequency domain to obtain the time-frequency spectrum X(t,f). The conversion formula is: ; represents a discrete time series, f is the frequency, Represents the time window function, and then calculates the spectrum average in each time window , and the standard deviation of the spectrum , and then calculate the smoothness of the spectrum, the calculation formula is: ; T is the total number of time windows, Indicates the smoothness of the spectrum; Calculate the spectrum entropy using the formula: ; represents the normalized power spectral density of the spectrum at time t and frequency f, C is a constant, represents spectral entropy; Calculate the spectrum centroid using the formula: ; represents the centroid of the spectrum at frequency f; Calculate the sound quality index using the following formula: ; F is the total frequency number, SQI stands for sound quality index; Based on the generated production quality coefficient, the production equipment with potential failure hazards is divided into high-risk production equipment and low-risk production equipment, which means: The generated production quality coefficient is compared with the preset production safety reference coefficient. If the generated production quality coefficient is greater than or equal to the preset production safety reference coefficient, the production operation equipment with potential failure hazards are classified as low-risk production operation equipment. If the generated production quality coefficient is less than the preset production safety reference coefficient, the production operation equipment with potential failure hazards are classified as high-risk production operation equipment. For high-risk production equipment, different levels of early warning signals are issued based on the production quality coefficient: Obtain the production quality coefficient of high-risk production equipment and the preset safety benchmark value, calculate the ratio of the production quality coefficient to the preset safety benchmark value, preset a warning interval-level form, and use the level corresponding to the warning interval in which the ratio of the production quality coefficient to the preset safety benchmark value falls as the level of the warning signal issued; For low-risk production equipment, intelligent control of maintenance frequency means: Get the preset standard maintenance time interval for low-risk production operation equipment, and then calculate the adjusted maintenance time interval: ; BSi is the standard maintenance time interval corresponding to the production equipment numbered i, k is the preset adjustment coefficient, PQC is the production quality coefficient, and M is the maintenance time interval after adjustment; For production equipment without potential failure hazards, intelligent control of the actual sampling frequency based on the initial sampling frequency means: Get the initial sampling frequency and the time interval between the production equipment without potential failure and the last time it was judged to have potential failure, and then substitute it into the control formula: ; Y is the sampling frequency after adjustment, R is a constant, v is the preset adjustment coefficient, and Ti is the time interval.

2. An automated container terminal production control system, based on the automated container terminal production control method according to claim 1, It is characterized in that It includes information collection module, preliminary judgment module, abnormal analysis module, classification module, early warning and control module; The information collection module is used to use sensors to capture the vibration information of various production equipment of the automated container terminal in real time at the initial sampling frequency; Preliminary judgment is used to pre-process the vibration information, then extract the vibration frequency characteristic data and conduct preliminary analysis to determine whether there are potential failure hazards in various production equipment of the automated container terminal; The abnormality analysis module is used to obtain operation information of production equipment with potential failure hazards, and then perform abnormality analysis to generate a power quality index and a sound quality index. The power quality index and the sound quality index are then transmitted to a pre-trained machine learning model to generate a production quality coefficient through the pre-trained machine learning model. The classification module is used to classify the production operation equipment with potential failure hazards into high-risk production operation equipment and low-risk production operation equipment based on the generated production quality coefficient; The early warning and control module includes an early warning unit, a maintenance control unit and a sampling control unit. The early warning unit is used to issue early warning signals of different levels based on the production quality coefficient for high-risk production equipment; the maintenance control unit is used to perform intelligent control of the maintenance frequency of low-risk production equipment; the sampling control unit is used to perform intelligent control of the actual sampling frequency of production equipment that does not have potential faults based on the initial sampling frequency.

Images