Big-data-based visual tallying method for container terminal

Abstract

The present invention relates to the technical field of terminal tallying. Disclosed is a big-data-based visual tallying method for a container terminal. The method comprises: on the basis of preset test time points and parameter collection devices, performing periodic parameter testing on a container tallying device, so as to obtain periodic feedback testing parameters; performing classification to obtain periodic feedback testing parameter sequences, and generating an initialization flag for the container tallying device; when an unknown initialization flag is detected, analyzing the periodic feedback testing parameter sequences, and calculating periodic feedback testing parameter coefficients; performing curve fitting to obtain a periodic feedback testing parameter coefficient curve, and calculating a tallying state assessment factor; and determining whether to intervene in a tallying behavior of the container tallying device, and if so, generating an intervention result on the basis of the tallying state assessment factor. Thus, the present invention realizes comprehensive monitoring and precise assessment, enhances the device fault early-warning capability, improves the tallying efficiency and safety, and effectively reduces tallying deviations and safety risks, thereby providing a scientific basis for terminal operations.

Description

Container terminal visual cargo handling method based on big data TECHNICAL FIELD

[0001] The present application relates to the technical field of terminal cargo handling, in particular to a container terminal visual cargo handling method based on big data. BACKGROUND

[0002] Terminal cargo handling is the work of counting, accepting, organizing storage and loading and unloading of import and export containers, which is a very important link in modern logistics transportation. Specifically, it includes cargo receiving and counting, organization of storage and loading and unloading, record and report, maintenance equipment and safety management, etc. With the continuous development of global trade and the continuous progress of logistics technology, terminal cargo handling work is constantly innovating and improving.

[0003] In the prior art, the running state evaluation of terminal cargo handling equipment mainly depends on manual visual inspection or single sensor detection, and this traditional method has obvious limitations. Specifically, the current evaluation method can only perform single analysis on basic parameters such as feedback voltage and feedback current during equipment operation, and cannot realize comprehensive analysis of multi-dimensional data. This single determination mode not only reduces the accuracy of equipment state evaluation, but also makes it difficult to establish a scientific risk warning mechanism and provide reliable data support for terminal cargo handling operations. When the cargo handling equipment is unstable, due to the lack of effective real-time monitoring and early warning, serious consequences such as cargo handling deviation and cargo damage are likely to occur. Especially in high-load operation environment, subtle changes in equipment performance may be ignored, which eventually leads to significant economic losses or safety accidents. SUMMARY

[0004] The present application provides a container terminal visual cargo handling method based on big data, which realizes comprehensive monitoring and accurate evaluation of the running state of terminal cargo handling equipment, significantly improves the reliability and fault warning capability of the equipment, effectively reduces the cargo handling deviation and safety risk, provides a scientific basis for terminal operation, and improves the cargo handling efficiency and safety.

[0005] In order to achieve the above purpose, the present application provides a container terminal visual cargo handling method based on big data, comprising:

[0006] A plurality of parameter acquisition devices are pre-deployed on the container cargo handling equipment, and the container cargo handling equipment is periodically detected based on a preset detection time and the parameter acquisition devices, to obtain a plurality of sets of periodic feedback detection parameters;

[0007] The periodic feedback detection parameters are classified to obtain a plurality of periodic feedback detection parameter sequences, the container handling equipment is judged based on the periodic feedback detection parameter sequences, and an initialization mark is generated, wherein the initialization mark includes a risk initialization mark, a safety initialization mark, and an unknown initialization mark;

[0008] When the unknown initialization mark is identified, the periodic feedback detection parameter sequences are analyzed, and a periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequences is calculated based on the analysis result;

[0009] The periodic feedback detection parameter coefficient of each periodic feedback detection parameter sequence is extracted, curve fitting is performed to obtain a corresponding periodic feedback detection parameter coefficient curve, and a handling state evaluation factor of the container handling equipment is calculated based on the periodic feedback detection parameter coefficient curve;

[0010] Based on the handling state evaluation factor and a preset handling state evaluation factor, it is determined whether to intervene in the handling behavior of the container handling equipment, and if so, an intervention result of the container handling equipment is generated based on the handling state evaluation factor.

[0011] Further, when the container handling equipment is judged based on the periodic feedback detection parameter sequences, and an initialization mark is generated, it includes:

[0012] A safety periodic feedback detection parameter corresponding to each periodic feedback detection parameter sequence is obtained;

[0013] The container handling equipment is judged based on the safety periodic feedback detection parameter, and when the periodic feedback detection parameters in the periodic feedback detection parameter sequences are all greater than or equal to the safety periodic feedback detection parameter, the risk initialization mark is generated for the container handling equipment;

[0014] When the periodic feedback detection parameters in the periodic feedback detection parameter sequences are all less than the safety periodic feedback detection parameter, the safety initialization mark is generated for the container handling equipment;

[0015] When the periodic feedback detection parameters in the periodic feedback detection parameter sequences are greater than or equal to the safety periodic feedback detection parameter, and there are periodic feedback detection parameters less than the safety periodic feedback detection parameter, the unknown initialization mark is generated for the container handling equipment.

[0016] Further, when the periodic feedback detection parameter sequences are analyzed, and a periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequences is calculated based on the analysis result, it includes:

[0017] generating analysis sequential numbers based on the acquisition time sequence of the periodic feedback detection parameter sequence;

[0018] determining a first periodic feedback detection parameter corresponding to a first analysis sequential number, and determining first periodic feedback detection parameter differences between the first periodic feedback detection parameter and all the other periodic feedback detection parameters;

[0019] selecting a first maximum periodic feedback detection parameter difference from all the first periodic feedback detection parameter differences, and generating a maximum difference identifier;

[0020] determining a second periodic feedback detection parameter corresponding to a second analysis sequential number, and determining second periodic feedback detection parameter differences between the second periodic feedback detection parameter and all the other periodic feedback detection parameters;

[0021] selecting a second maximum periodic feedback detection parameter difference from all the second periodic feedback detection parameter differences, and generating a maximum difference identifier;

[0022] analyzing the periodic feedback detection parameters corresponding to the remaining analysis sequential numbers, and determining a plurality of maximum difference identifiers;

[0023] extracting the maximum periodic feedback detection parameter differences corresponding to all the maximum difference identifiers, and determining whether there are identical maximum periodic feedback detection parameter differences, if there are, calculating the identical difference sum of all the identical maximum periodic feedback detection parameter differences;

[0024] calculating the non-identical difference sum of the remaining maximum periodic feedback detection parameter differences corresponding to the maximum difference identifier;

[0025] determining the ratio of the identical difference sum and the non-identical difference sum as the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence;

[0026] if not, selecting a maximum parameter difference and a minimum parameter difference from the maximum periodic feedback detection parameter differences corresponding to the maximum difference identifiers;

[0027] calculating the range sum of the maximum parameter difference and the minimum parameter difference;

[0028] calculating the remaining difference sum of the remaining maximum periodic feedback detection parameter differences corresponding to the maximum difference identifier;

[0029] determining the ratio of the range sum and the remaining difference sum as the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence.

[0030] Further, in calculating the evaluation factor of the container handling equipment based on the periodic feedback detection parameter coefficient curve, comprising:

[0031] determining the coefficient slope corresponding to each periodic feedback detection parameter coefficient on the periodic feedback detection parameter coefficient curve, and constructing a calculation coefficient e w , wherein e is a constant, and w is the coefficient slope;

[0032] determining the coefficient mean corresponding to all periodic feedback detection parameter coefficients on the periodic feedback detection parameter coefficient curve;

[0033] respectively calculating the product value of each calculation coefficient and the coefficient mean as a sub-evaluation factor of the handling state;

[0034] calculating the evaluation factor of the container handling equipment according to all sub-evaluation factors of the handling state.

[0035] Further, in calculating the evaluation factor of the container handling equipment according to all sub-evaluation factors of the handling state, comprising:

[0036] calculating the evaluation factor of the container handling equipment according to the following formula:

[0037] ;

[0038] ;

[0039] ;

[0040] , wherein q is the evaluation factor of the container handling equipment, r1 is the first calculation factor, r2 is the second calculation factor, max is the maximum value symbol, p is the number of sub-evaluation factors of the handling state, y u is the u-th sub-evaluation factor of the handling state, y1 is the variance of all sub-evaluation factors of the handling state, y2 is the mean of all sub-evaluation factors of the handling state, and y3 is the standard deviation of all sub-evaluation factors of the handling state.

[0041] Further, in determining whether to intervene in the handling behavior of the container handling equipment based on the evaluation factor of the handling state and a preset evaluation factor of the handling state, comprising:

[0042] When the evaluation factor of the handling state is less than the preset evaluation factor of the handling state, it is determined that no intervention is made in the handling behavior of the container handling equipment, and a safety mark is generated for the container handling equipment;

[0043] When the tallying state evaluation factor is greater than or equal to the preset tallying state evaluation factor, it is determined to intervene in the tallying behavior of the container tallying equipment, and a risk mark is generated for the container tallying equipment.

[0044] Further, when the intervention result of the container tallying equipment is generated based on the tallying state evaluation factor, it includes:

[0045] The historical tallying behaviors of the container tallying equipment within a preset time are collected, the historical tallying behaviors are analyzed, and the historical tallying behaviors are divided into historical deviation tallying behaviors and historical compliance tallying behaviors;

[0046] The historical tallying deviation value corresponding to each historical deviation tallying behavior is determined;

[0047] The number of historical deviation tallying behaviors of the historical deviation tallying behaviors is counted, and the number of historical compliance tallying behaviors of the historical compliance tallying behaviors is counted;

[0048] The historical tallying behavior value of the container tallying equipment is calculated based on the historical tallying deviation value, the number of historical deviation tallying behaviors, and the number of historical compliance tallying behaviors;

[0049] The tallying state evaluation factor is adjusted according to the historical tallying behavior value, to obtain an intervention tallying state evaluation factor of the container tallying equipment, and an intervention result of the container tallying equipment is generated based on the intervention tallying state evaluation factor.

[0050] Further, when the intervention tallying state evaluation factor of the container tallying equipment is obtained by adjusting the tallying state evaluation factor according to the historical tallying behavior value, it includes:

[0051] A plurality of preset historical tallying behavior values are preset;

[0052] A plurality of preset evaluation factor adjustment values are preset;

[0053] According to the historical tallying behavior value and the plurality of preset historical tallying behavior values, a corresponding preset evaluation factor adjustment value is selected, wherein the historical tallying behavior value and the preset evaluation factor adjustment value are in a positive proportional relationship;

[0054] The product value of the selected preset evaluation factor adjustment value and the tallying state evaluation factor is calculated as the intervention tallying state evaluation factor of the container tallying equipment.

[0055] Further, when the intervention result of the container tallying equipment is generated based on the intervention tallying state evaluation factor, it includes:

[0056] A preset intervention unloading state evaluation factor is preset, when the intervention unloading state evaluation factor is less than the preset intervention unloading state evaluation factor, an online maintenance result is generated for the container unloading equipment;

[0057] When the intervention unloading state evaluation factor is greater than or equal to the preset intervention unloading state evaluation factor, a shutdown maintenance result is generated for the container unloading equipment.

[0058] Compared with the prior art, the present application has the following beneficial effects:

[0059] The application discloses a kind of based on big data container wharf visual unloading method, based on preset detection time and parameter acquisition equipment is periodically detected to container unloading equipment parameter, obtains periodic feedback detection parameter, is classified, obtains periodic feedback detection parameter sequence, generates initialization mark to container unloading equipment.When unknown initialization mark is identified, periodic feedback detection parameter sequence is analyzed, periodic feedback detection parameter coefficient is calculated, curve fitting is carried out, and periodic feedback detection parameter coefficient curve is obtained, and unloading state evaluation factor is calculated.Judge whether the unloading behavior of container unloading equipment is intervened, if yes, then based on unloading state evaluation factor generates intervention result, realizes comprehensive monitoring and accurate evaluation, improves equipment fault early warning capability, improves unloading efficiency and safety, effectively reduces unloading deviation and safety risk, provides scientific basis for wharf operation. BRIEF DESCRIPTION OF DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of the preferred embodiments and are not intended to limit the scope of the application. Furthermore, the same reference numerals are intended to denote the same components throughout the accompanying drawings. In the drawings:

[0061] Fig. 1 shows a flowchart of a kind of based on big data container wharf visual unloading method in the embodiment of the application. DETAILED DESCRIPTION

[0062] The specific embodiments of the present application will be further described in detail below in conjunction with the drawings and examples. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0063] In the description of the present application, it should be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0064] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0065] In the description of the present application, it should be noted that unless otherwise specified and limited, the terms "mounting", "connecting", "connecting" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be directly connected, or indirectly connected through intermediate medium, or the communication inside two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0066] The following is a description of the preferred embodiments of the present application in conjunction with the drawings.

[0067] As shown in FIG. 1, the embodiments of the present application disclose a container terminal visual cargo method based on big data, comprising:

[0068] S110: Pre-deploy a plurality of parameter acquisition devices on the container cargo equipment, periodically detect the container cargo equipment based on the preset detection time and the parameter acquisition device, and obtain a plurality of groups of periodic feedback detection parameters;

[0069] In this embodiment, when handling containers, the handling equipment involved includes mobile handling gates, container trucks, cameras, etc. The mobile handling gates adopt a gantry structure, and the information data such as container truck number and container number are efficiently collected and recognized by the camera. The photovoltaic solar panel + energy storage battery is used to provide power, realizing green and sustainable use. The overall size of the mobile handling gate is 6000*6000*4000mm, which is composed of a gantry, an equipment box, a camera, a wireless network bridge, a photovoltaic panel, etc. The gantry frame structure is made of galvanized steel pipe, the column beams and cross beams around the frame are made of 100*100mm galvanized steel pipe, and the column beams and cross beams inside the frame are made of 50*50mm galvanized steel pipe. The equipment box contains battery packs, reverse control integrated machines, power distribution modules, switches and identification integrated machines, etc. There are 5 cameras, 3 of which are installed at the top and 1 on each side. The new generation of spliced cameras can make the container face information clear and complete, and the truck number and container number recognition accuracy is high. Four photovoltaic panels are installed at the top to provide green power. Realizing green and sustainable use, the container truck passes through the mobile handling gate, and the spliced camera and the identification integrated machine work during the process, outputting identification records including truck number, container number, container face photos, etc. The photovoltaic panel generates electricity and is transmitted to the energy storage battery, which outputs 220V power through the reverse control integrated machine for the camera and equipment integrated machine.

[0070] In this embodiment, the container handling equipment is the container truck described above.

[0071] In this embodiment, the parameter collection device includes a voltage sensor, a current sensor, a vibration sensor, a motor speed sensor, etc., which are not shown one by one here.

[0072] In this embodiment, the preset detection time is set in advance, and the preferred values are the 10th second, the 20th second, the 30th second, the 40th second, the 50th second, the 60th second, the 70th second, the 80th second, the 90th second and the 100th second. Here, 10 preset detection times are set, and the specific values can also be adjusted according to actual needs.

[0073] In this embodiment, a set of periodic feedback detection parameters can be collected at each preset detection time, that is, 10 sets of periodic feedback detection parameters can be collected.

[0074] In this embodiment, the periodic feedback detection parameters include voltage parameters, current parameters, vibration parameters, motor speed parameters, etc., which are not shown one by one here.

[0075] The beneficial effects of the above technical solutions are that the mobile tallying gate helps to realize the intelligence and automation of the port. Through the integration of Internet of Things, big data, artificial intelligence and other technologies, the mobile tallying gate can realize functions such as automatic confirmation of containers, automatic sending of information, remote monitoring, etc., so that the loading and unloading of port goods are more intelligent and automated. This will further improve the operation efficiency and service quality of the port, enhance the competitiveness of the port, and provide reliable data support for subsequent evaluation by collecting multiple sets of periodic feedback detection parameters, ensuring the comprehensiveness of data collection.

[0076] S120: classifying each set of periodic feedback detection parameters to obtain multiple periodic feedback detection parameter sequences, performing initialization judgment on the container tallying equipment based on the periodic feedback detection parameter sequences, and generating an initialization mark, wherein the initialization mark includes a risk initialization mark, a safety initialization mark and an unknown initialization mark;

[0077] In this embodiment, classifying each set of periodic feedback detection parameters means classifying parameters of the same type corresponding to each preset detection time, such as classifying the voltage parameter at the 10th second, the voltage parameter at the 20th second, etc., to obtain a periodic feedback detection parameter sequence with only voltage parameters.

[0078] In some embodiments of the present application, when performing initialization judgment on the container tallying equipment based on the periodic feedback detection parameter sequences and generating an initialization mark, it includes:

[0079] Obtaining a safety periodic feedback detection parameter corresponding to each periodic feedback detection parameter sequence;

[0080] Performing initialization judgment on the container tallying equipment based on the safety periodic feedback detection parameter, and when the periodic feedback detection parameters in the periodic feedback detection parameter sequence are all greater than or equal to the safety periodic feedback detection parameter, generating the risk initialization mark for the container tallying equipment;

[0081] When the periodic feedback detection parameters in the periodic feedback detection parameter sequence are all less than the safety periodic feedback detection parameter, the safety initialization mark is generated for the container tallying equipment;

[0082] When the periodic feedback detection parameters in the periodic feedback detection parameter sequence are greater than or equal to the safety periodic feedback detection parameter and less than the safety periodic feedback detection parameter, the unknown initialization mark is generated for the container tallying equipment.

[0083] In the embodiment, the safety periodic feedback detection parameter is set in advance and corresponds to the periodic feedback detection parameter sequence one by one, for example, the safety voltage parameter is set to 15V, and the rest is set according to the actual situation.

[0084] In the embodiment, when the risk initialization mark is detected, the container handling equipment is directly reminded to stop and overhaul.

[0085] In the embodiment, the unknown initialization mark means that it cannot be directly judged whether the container handling equipment has a running risk, and further judgment is needed.

[0086] The beneficial effects of the above technical scheme are: the application initializes and judges the container handling equipment based on the safety periodic feedback detection parameter, generates an initialization mark, realizes the initialization judgment of the container handling equipment, and avoids the container handling equipment with high risk.

[0087] S130: When the unknown initialization mark is identified, the periodic feedback detection parameter sequence is analyzed, and the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence is calculated based on the analysis result;

[0088] In some embodiments of the application, when the periodic feedback detection parameter sequence is analyzed and the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence is calculated based on the analysis result, it includes:

[0089] An analysis sequence number is generated based on the periodic feedback detection parameters in the periodic feedback detection parameter sequence in the order of collection time;

[0090] A first periodic feedback detection parameter corresponding to a first analysis sequence number is determined, and a first periodic feedback detection parameter difference between all remaining periodic feedback detection parameters and the first periodic feedback detection parameter is determined;

[0091] A first maximum periodic feedback detection parameter difference is selected from all first periodic feedback detection parameter differences, and a maximum difference identifier is generated;

[0092] A second periodic feedback detection parameter corresponding to a second analysis sequence number is determined, and a second periodic feedback detection parameter difference between all remaining periodic feedback detection parameters and the second periodic feedback detection parameter is determined;

[0093] A second maximum periodic feedback detection parameter difference is selected from all second periodic feedback detection parameter differences, and a maximum difference identifier is generated;

[0094] The periodic feedback detection parameters corresponding to the remaining analysis sequence numbers are analyzed to determine a plurality of maximum difference identifiers;

[0095] extracting all the maximum difference values to identify corresponding maximum periodic feedback detection parameter difference values, and determining whether there are same maximum periodic feedback detection parameter difference values, if there are, calculating same difference sum values of all the same maximum periodic feedback detection parameter difference values;

[0096] calculating non-same difference sum values of the remaining maximum periodic feedback detection parameter difference values corresponding to the maximum difference values identified;

[0097] determining a ratio of the same difference sum values and the non-same difference sum values as a periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence;

[0098] if there are not, selecting a maximum parameter difference value and a minimum parameter difference value from the maximum periodic feedback detection parameter difference values corresponding to the maximum difference values identified;

[0099] calculating a range difference sum value of the maximum parameter difference value and the minimum parameter difference value;

[0100] calculating a remaining difference sum value of the remaining maximum periodic feedback detection parameter difference values corresponding to the maximum difference values identified;

[0101] determining a ratio of the range difference sum value and the remaining difference sum value as a periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence.

[0102] In the embodiment, the analysis sequence numbers are S1, S2, S3, and the like, and the number of the periodic feedback detection parameters is consistent with the number of the analysis sequence numbers.

[0103] In the embodiment, the first analysis sequence number is S1.

[0104] In the embodiment, the first periodic feedback detection parameter difference value refers to a value obtained by subtracting the first periodic feedback detection parameter from all the periodic feedback detection parameters.

[0105] In the embodiment, the second periodic feedback detection parameter difference value refers to a value obtained by subtracting the second periodic feedback detection parameter from all the periodic feedback detection parameters.

[0106] In the embodiment, the periodic feedback detection parameter difference values corresponding to the remaining analysis sequence numbers are not illustrated one by one.

[0107] In the embodiment, the maximum parameter difference value refers to a maximum value in all the maximum periodic feedback detection parameter difference values, and the minimum parameter difference value refers to a minimum value in all the maximum periodic feedback detection parameter difference values.

[0108] The beneficial effects of the above technical solutions are: the ratio of the same difference sum and the different difference sum is determined as the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence; or the ratio of the range sum and the remaining difference sum is determined as the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence. Two different calculation methods are provided for the two different situations, which ensures the calculation accuracy of the periodic feedback detection parameter coefficient. The periodic feedback detection parameter coefficient can reflect the overall parameter change of the periodic feedback detection parameter sequence, and comprehensive analysis is realized.

[0109] S140: Extract the periodic feedback detection parameter coefficient of each periodic feedback detection parameter sequence, perform curve fitting to obtain the corresponding periodic feedback detection parameter coefficient curve, and calculate the handling state evaluation factor of the container handling equipment based on the periodic feedback detection parameter coefficient curve;

[0110] In this embodiment, the fixed values are taken as the abscissa, which are 1, 2, 3, 4, 5, 6, etc., which are an arithmetic sequence. The specific number of settings is consistent with the number of periodic feedback detection parameter coefficients. All periodic feedback detection parameters are fitted based on the extraction sequence.

[0111] In some embodiments of the present application, when the handling state evaluation factor of the container handling equipment is calculated based on the periodic feedback detection parameter coefficient curve, it includes:

[0112] Determine the coefficient slope corresponding to each periodic feedback detection parameter coefficient on the periodic feedback detection parameter coefficient curve, and construct a calculation coefficient e w Wherein e is a constant, and w is the coefficient slope.

[0113] Determine the coefficient mean corresponding to all periodic feedback detection parameter coefficients on the periodic feedback detection parameter coefficient curve;

[0114] Calculate the product value of each calculation coefficient and the coefficient mean respectively as a sub-handling state evaluation factor;

[0115] Calculate the handling state evaluation factor of the container handling equipment according to all sub-handling state evaluation factors.

[0116] In this embodiment, the determination method of the slope is no longer introduced.

[0117] The beneficial effects of the above technical solutions are that the application calculates the product value of each calculation coefficient and the coefficient mean value respectively as a sub-tallying state evaluation factor, lays a foundation for calculating a tallying state evaluation factor, calculates the tallying state evaluation factor of the container tallying equipment according to all sub-tallying state evaluation factors, guarantees the calculation accuracy and calculation efficiency of the tallying state evaluation factor, and can also reflect the running state of the container tallying equipment, without manual participation in calculation and determination, and eliminates the evaluation subjectivity and errors.

[0118] In some embodiments of the application, when the tallying state evaluation factor of the container tallying equipment is calculated according to all sub-tallying state evaluation factors, the following is included:

[0119] The tallying state evaluation factor of the container tallying equipment is calculated according to the following formula:

[0120] ;

[0121] ;

[0122] ;

[0123] Wherein, q is the tallying state evaluation factor of the container tallying equipment, r1 is the first calculation factor, r2 is the second calculation factor, max is the maximum value symbol, p is the number of sub-tallying state evaluation factors, y u is the u-th sub-tallying state evaluation factor, y1 is the variance of all sub-tallying state evaluation factors, y2 is the mean value of all sub-tallying state evaluation factors, and y3 is the standard deviation of all sub-tallying state evaluation factors.

[0124] S150: determining whether to intervene in the tallying behavior of the container tallying equipment based on the tallying state evaluation factor and a preset tallying state evaluation factor, and if so, generating an intervention result of the container tallying equipment based on the tallying state evaluation factor.

[0125] In some embodiments of the application, when it is determined whether to intervene in the tallying behavior of the container tallying equipment based on the tallying state evaluation factor and a preset tallying state evaluation factor, the following is included:

[0126] When the tallying state evaluation factor is less than the preset tallying state evaluation factor, it is determined not to intervene in the tallying behavior of the container tallying equipment, and a safety mark is generated for the container tallying equipment;

[0127] When the tallying state evaluation factor is greater than or equal to the preset tallying state evaluation factor, it is determined to intervene in the tallying behavior of the container tallying equipment, and a risk mark is generated for the container tallying equipment.

[0128] In this embodiment, the preset tallying state evaluation factor is set in advance, which is preferably 12, and can also be adjusted according to actual conditions.

[0129] The above technical solution has the beneficial effects that when the tallying state evaluation factor is less than the preset tallying state evaluation factor, the tallying behavior is not intervened, and a safety mark is generated, at this time, it is normal fluctuation of the periodic feedback detection parameter, and there is no operation risk, when the tallying state evaluation factor is greater than or equal to the preset tallying state evaluation factor, the tallying behavior is intervened, and a risk mark is generated, at this time, the container tallying device has a risk operation, and further measures need to be taken to avoid the risk increase.

[0130] In some embodiments of the present application, when the intervention result of the container tallying device is generated based on the tallying state evaluation factor, it includes:

[0131] The historical tallying behaviors of the container tallying device in a preset time are collected, the historical tallying behaviors are analyzed, and the historical tallying behaviors are divided into historical deviation tallying behaviors and historical compliance tallying behaviors;

[0132] The historical tallying deviation value corresponding to each historical deviation tallying behavior is determined;

[0133] The number of historical deviation tallying behaviors of the historical deviation tallying behaviors is counted, and the number of historical compliance tallying behaviors of the historical compliance tallying behaviors is counted;

[0134] The historical tallying behavior value of the container tallying device is calculated based on the historical tallying deviation value, the number of historical deviation tallying behaviors and the number of historical compliance tallying behaviors;

[0135] The tallying state evaluation factor is adjusted according to the historical tallying behavior value, to obtain the intervention tallying state evaluation factor of the container tallying device, and the intervention result of the container tallying device is generated based on the intervention tallying state evaluation factor.

[0136] In this embodiment, collecting the historical tallying behaviors of the container tallying device in a preset time means collecting the historical tallying behaviors of the container tallying device in the past one day, from loading the container to placing the container in the standard placement position as one historical tallying behavior, and the preset time is the past one day.

[0137] In this embodiment, when the actual placement position of the container does not conform to the standard placement position during the container is placed, the corresponding historical tallying behavior is judged as a historical deviation tallying behavior, and if it conforms, the corresponding historical tallying behavior is judged as a historical compliance tallying behavior.

[0138] In the embodiment, when determining the historical deviation value corresponding to each historical deviation handling behavior, the historical deviation value can be determined according to the following manner:

[0139] obtaining a standard placement image and an actual placement image of the container;

[0140] performing preprocessing on the standard placement image and the actual placement image, including image denoising, grayscale, and edge detection;

[0141] extracting a position contour in the standard placement image as a reference contour;

[0142] extracting a position contour in the actual placement image as an actual contour;

[0143] aligning the reference contour with the actual contour, calculating a deviation therebetween, and taking the deviation as a historical deviation value, wherein the deviation calculation includes at least one of a translation deviation, a rotation deviation, and a scaling deviation.

[0144] In the embodiment, the historical handling behavior value of the container handling equipment is calculated according to the following formula:

[0145] ;

[0146] wherein d is the historical handling behavior value of the container handling equipment, f1 is a first calculation coefficient, which is preferably 0.3 herein, g1 is the number of historical deviation handling behaviors, g2 is the number of historical compliant handling behaviors, f2 is a second calculation coefficient, which is preferably 0.7 herein, and h j is the jth historical deviation value, h max is the maximum historical deviation value.

[0147] The beneficial effects of the above technical solution are that the historical handling behavior value of the container handling equipment is calculated based on the historical deviation value, the number of historical deviation handling behaviors, and the number of historical compliant handling behaviors, the historical handling behavior value can reflect the historical handling placement situation of the container handling equipment, when the historical handling behavior value is larger, it indicates that the historical handling placement situation of the container handling equipment is worse, and vice versa, when the historical handling behavior value is smaller, it indicates that the historical handling placement situation of the container handling equipment is better, the generation accuracy of the intervention result can be ensured by calculating the historical handling behavior value, and the normal operation of the handling work is avoided from being affected.

[0148] In some embodiments of the present application, when the handling state evaluation factor of the container handling equipment is adjusted according to the historical handling behavior value, an intervention handling state evaluation factor of the container handling equipment is obtained, which includes:

[0149] a plurality of preset historical handling behavior values are preset in advance;

[0150] a plurality of preset evaluation factor adjustment values are preset;

[0151] a corresponding preset evaluation factor adjustment value is selected according to the historical handling behavior value and the plurality of preset historical handling behavior values, wherein the historical handling behavior value and the preset evaluation factor adjustment value are in a positive proportional relationship;

[0152] a product value of the selected preset evaluation factor adjustment value and the handling status evaluation factor is calculated as the intervention handling status evaluation factor of the container handling equipment.

[0153] In the embodiment, the number of preset historical handling behavior values is preferably three, including a first preset historical handling behavior value, a second preset historical handling behavior value, and a third preset historical handling behavior value, wherein the first preset historical handling behavior value is preferably 4, the second preset historical handling behavior value is preferably 6, and the third preset historical handling behavior value is preferably 8, which can also be adjusted according to actual conditions.

[0154] In the embodiment, the number of preset evaluation factor adjustment values is preferably four, including a first preset evaluation factor adjustment value, a second preset evaluation factor adjustment value, a third preset evaluation factor adjustment value, and a fourth preset evaluation factor adjustment value, wherein the first preset evaluation factor adjustment value is preferably 0.85, the second preset evaluation factor adjustment value is preferably 0.9, the third preset evaluation factor adjustment value is preferably 1.1, and the fourth preset evaluation factor adjustment value is preferably 1.15, which can also be adjusted according to actual conditions.

[0155] In the embodiment, when the historical handling behavior value is less than the first preset historical handling behavior value, a first product value of the first preset evaluation factor adjustment value and the handling status evaluation factor is calculated as the intervention handling status evaluation factor of the container handling equipment. When the historical handling behavior value is greater than or equal to the first preset historical handling behavior value and less than the second preset historical handling behavior value, a second product value of the second preset evaluation factor adjustment value and the handling status evaluation factor is calculated as the intervention handling status evaluation factor of the container handling equipment. When the historical handling behavior value is greater than or equal to the second preset historical handling behavior value and less than the third preset historical handling behavior value, a third product value of the third preset evaluation factor adjustment value and the handling status evaluation factor is calculated as the intervention handling status evaluation factor of the container handling equipment. When the historical handling behavior value is greater than or equal to the fourth preset historical handling behavior value, a fourth product value of the fourth preset evaluation factor adjustment value and the handling status evaluation factor is calculated as the intervention handling status evaluation factor of the container handling equipment.

[0156] The beneficial effects of the above technical solutions are: according to the historical tallying behavior value and a plurality of preset historical tallying behavior values, a corresponding preset evaluation factor adjustment value is selected, dynamic adjustment of the tallying state evaluation factor is realized, the tallying state evaluation factor of the container tallying equipment is comprehensively considered in combination with the historical tallying behavior value, that is, the real-time running state of the container tallying equipment is considered in combination with the historical running state, the dynamic adjustment precision is ensured, the generation precision of the intervention result is effectively improved, and errors are eliminated.

[0157] In some embodiments of the present application, when the intervention result of the container tallying equipment is generated based on the intervention tallying state evaluation factor, the following is included:

[0158] A preset intervention tallying state evaluation factor is preset, and when the intervention tallying state evaluation factor is less than the preset intervention tallying state evaluation factor, an online maintenance result is generated for the container tallying equipment.

[0159] When the intervention tallying state evaluation factor is greater than or equal to the preset intervention tallying state evaluation factor, a shutdown maintenance result is generated for the container tallying equipment.

[0160] In the embodiment, the preset intervention tallying state evaluation factor is preferably 16, and can also be adjusted according to actual conditions.

[0161] The beneficial effects of the above technical solutions are: online maintenance refers to small-scale inspection and repair during equipment operation, ensuring continuous and efficient operation of the equipment. Shutdown maintenance refers to large-scale inspection and repair after the equipment stops running, solving potential or existing serious faults. Generating an online maintenance result helps to discover and handle small problems of the equipment in a timely manner, avoids the influence of shutdown on the tallying work, improves efficiency, and generating a shutdown maintenance result can prevent serious faults of the equipment, ensure safe operation, and reduce losses.

Claims

1. A big data based container terminal visualized tallying method, characterized in that, The method comprises the following steps: Pre-deploy a plurality of parameter acquisition devices on the container handling equipment, periodically detect the container handling equipment based on a preset detection time and the parameter acquisition devices, and obtain a plurality of sets of periodic feedback detection parameters; Classify each set of periodic feedback detection parameters to obtain a plurality of periodic feedback detection parameter sequences, perform initialization judgment on the container handling equipment based on the periodic feedback detection parameter sequences, and generate an initialization mark, wherein the initialization mark includes a risk initialization mark, a safety initialization mark, and an unknown initialization mark; When the unknown initialization mark is identified, analyze the periodic feedback detection parameter sequence, and calculate the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence based on the analysis result; Extract the periodic feedback detection parameter coefficient of each periodic feedback detection parameter sequence, perform curve fitting to obtain the corresponding periodic feedback detection parameter coefficient curve, and calculate the handling state evaluation factor of the container handling equipment based on the periodic feedback detection parameter coefficient curve; Based on the handling state evaluation factor and the preset handling state evaluation factor, determine whether to intervene in the handling behavior of the container handling equipment, and if so, generate an intervention result of the container handling equipment based on the handling state evaluation factor; When analyzing the periodic feedback detection parameter sequence and calculating the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence based on the analysis result, the method comprises the following steps: Generate an analysis sequence number for the periodic feedback detection parameters in the periodic feedback detection parameter sequence based on the collection time sequence; Determine the first periodic feedback detection parameter corresponding to the first analysis sequence number, and determine the first periodic feedback detection parameter difference value corresponding to the first periodic feedback detection parameter and all the remaining periodic feedback detection parameters; Select the first maximum periodic feedback detection parameter difference value from all the first periodic feedback detection parameter difference values, and generate a maximum difference value mark; Determine the second periodic feedback detection parameter corresponding to the second analysis sequence number, and determine the second periodic feedback detection parameter difference value corresponding to the second periodic feedback detection parameter and all the remaining periodic feedback detection parameters; Select the second maximum periodic feedback detection parameter difference value from all the second periodic feedback detection parameter difference values, and generate a maximum difference value mark; Analyze the periodic feedback detection parameters corresponding to the remaining analysis sequence numbers, and determine a plurality of maximum difference value marks; Extract the maximum periodic feedback detection parameter difference values corresponding to all the maximum difference value marks, and determine whether there are identical maximum periodic feedback detection parameter difference values, if so, calculate the same difference sum value of all the identical maximum periodic feedback detection parameter difference values; Calculate the different difference sum value of the remaining maximum periodic feedback detection parameter difference values corresponding to the maximum difference value mark; Determine the ratio of the same difference sum value and the different difference sum value as the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence; If not, the maximum parameter difference value and the minimum parameter difference value are selected from the maximum difference value identification corresponding maximum periodic feedback detection parameter difference value; The range value and value of the maximum parameter difference value and the minimum parameter difference value are calculated; The residual difference value and value of the remaining maximum periodic feedback detection parameter difference value corresponding to the maximum difference value identification are calculated; The ratio of the range value and value and the residual difference value and value is determined as the periodic feedback detection parameter coefficient of the periodic feedback detection parameter sequence.

2. The big data based container terminal visualized tallying method according to claim 1, wherein, When the container handling equipment is initialized based on the periodic feedback detection parameter sequence and an initialization mark is generated, it includes: Obtain the safe periodic feedback detection parameter corresponding to each periodic feedback detection parameter sequence; Based on the safe periodic feedback feedback detection parameter, the container handling equipment is initialized, and when the periodic feedback detection parameters in the periodic feedback detection parameter sequence are all greater than or equal to the safe periodic feedback detection parameter, the container handling equipment generates the risk initialization mark; When the periodic feedback detection parameters in the periodic feedback detection parameter sequence are all less than the safe periodic feedback detection parameter, the container handling equipment generates the safe initialization mark; When the periodic feedback detection parameters in the periodic feedback detection parameter sequence are greater than or equal to the safe periodic feedback detection parameter, and there are less than the safe periodic feedback detection parameter, the container handling equipment generates the unknown initialization mark.

3. The big data based container terminal visualized tallying method according to claim 1, wherein, When the handling state evaluation factor of the container handling equipment is calculated based on the periodic feedback detection parameter coefficient curve, it includes: determining the coefficient slope corresponding to each periodic feedback detection parameter coefficient on the periodic feedback detection parameter coefficient curve, and constructing a calculation coefficient e w wherein e is a constant and w is the coefficient slope; Determine the coefficient mean value corresponding to all periodic feedback detection parameter coefficients on the periodic feedback detection parameter coefficient curve; Calculate the product value of each calculation coefficient and the coefficient mean value respectively as a sub-handling state evaluation factor; According to all the sub-handling state evaluation factors, the handling state evaluation factor of the container handling equipment is calculated.

4. The big data based container terminal visualized tallying method according to claim 3, wherein, When the handling state evaluation factor of the container handling equipment is calculated according to all the sub-handling state evaluation factors, it includes: The handling state evaluation factor of the container handling equipment is calculated according to the following formula: ； ； ； wherein q is a tallying state evaluation factor of the container tallying device, r1 is a first calculation factor, r2 is a second calculation factor, max is a maximum value symbol, p is a number of sub-tallying state evaluation factors, y u is the u-th sub-tallying state evaluation factor, y1 is a variance of all sub-tallying state evaluation factors, y2 is a mean of all sub-tallying state evaluation factors, and y3 is a standard deviation of all sub-tallying state evaluation factors.

5. The big data based container port visualized tallying method according to claim 1, wherein, When it is judged whether to intervene in the handling behavior of the container handling equipment based on the handling state evaluation factor and the preset handling state evaluation factor, it includes: When the handling state evaluation factor is less than the preset handling state evaluation factor, it is judged that the handling behavior of the container handling equipment is not intervened, and the safe mark is generated for the container handling equipment; When the handling state evaluation factor is greater than or equal to the preset handling state evaluation factor, it is judged that the handling behavior of the container handling equipment is intervened, and the risk mark is generated for the container handling equipment.

6. The big data based container port visualized tallying method according to claim 1, wherein, When the intervention result of the container handling equipment is generated based on the handling state evaluation factor, it includes: Collect the historical handling behavior of the container handling equipment within a preset time, analyze the historical handling behavior, and divide the historical handling behavior into historical deviation handling behavior and historical compliance handling behavior; Determine a historical deviation handling value corresponding to each historical deviation handling behavior; Count the number of historical deviation handling behaviors of the historical deviation handling behaviors, and count the number of historical compliance handling behaviors of the historical compliance handling behaviors; Calculate a historical handling behavior value of the container handling equipment based on the historical deviation handling value, the number of historical deviation handling behaviors, and the number of historical compliance handling behaviors; Adjust the handling state evaluation factor according to the historical handling behavior value to obtain an intervention handling state evaluation factor of the container handling equipment, and generate an intervention result of the container handling equipment based on the intervention handling state evaluation factor.

7. The big data based container terminal visualized tallying method according to claim 6, wherein, When adjusting the handling state evaluation factor according to the historical handling behavior value to obtain an intervention handling state evaluation factor of the container handling equipment, the method comprises: Pre-set a plurality of preset historical handling behavior values; Pre-set a plurality of preset evaluation factor adjustment values; Select a corresponding preset evaluation factor adjustment value according to the historical handling behavior value and the plurality of preset historical handling behavior values, wherein the historical handling behavior value and the preset evaluation factor adjustment value are in a positive proportional relationship; Calculate a product value of the selected preset evaluation factor adjustment value and the handling state evaluation factor as the intervention handling state evaluation factor of the container handling equipment.

8. The big data based container port visualized tallying method according to claim 6, wherein, When generating the intervention result of the container handling equipment based on the intervention handling state evaluation factor, the method comprises: Pre-set a preset intervention handling state evaluation factor, and when the intervention handling state evaluation factor is less than the preset intervention handling state evaluation factor, an online maintenance result is generated for the container handling equipment; When the intervention handling state evaluation factor is greater than or equal to the preset intervention handling state evaluation factor, a shutdown maintenance result is generated for the container handling equipment.

Images