CN116308003B - Dangerous goods automatic loading and unloading safety test method based on machine learning - Google Patents
Dangerous goods automatic loading and unloading safety test method based on machine learning Download PDFInfo
- Publication number
- CN116308003B CN116308003B CN202310067758.6A CN202310067758A CN116308003B CN 116308003 B CN116308003 B CN 116308003B CN 202310067758 A CN202310067758 A CN 202310067758A CN 116308003 B CN116308003 B CN 116308003B
- Authority
- CN
- China
- Prior art keywords
- data
- unloading
- dangerous goods
- automatic loading
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010801 machine learning Methods 0.000 title claims abstract description 37
- 238000009781 safety test method Methods 0.000 title claims abstract description 28
- 238000012417 linear regression Methods 0.000 claims abstract description 32
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000004519 manufacturing process Methods 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012549 training Methods 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 28
- 238000012795 verification Methods 0.000 claims description 27
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000011076 safety test Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013475 authorization Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 239000000383 hazardous chemical Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 10
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- QQONPFPTGQHPMA-UHFFFAOYSA-N propylene Natural products CC=C QQONPFPTGQHPMA-UHFFFAOYSA-N 0.000 description 1
- 125000004805 propylene group Chemical group [H]C([H])([H])C([H])([*:1])C([H])([H])[*:2] 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Algebra (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Factory Administration (AREA)
Abstract
The application discloses a safety test method for automatic loading and unloading of dangerous goods based on machine learning, which comprises the steps of collecting related data of automatic loading and unloading of dangerous goods, and preprocessing the data; constructing a linear regression algorithm model of machine learning according to the preprocessed parameters, and training and testing the data of the input model correspondingly; outputting the trained and tested results, and applying the results to actual production processes. The method can realize the optimized operation of automatic loading and unloading of the dangerous goods through the optimizing algorithm of machine learning, thereby improving the safety of loading and unloading the dangerous goods, and improving the working efficiency through the optimized operation method and related data.
Description
Technical Field
The application relates to the technical field of machine learning, in particular to a dangerous goods automatic loading and unloading safety test method based on machine learning.
Background
At present, the automatic loading and unloading mode of dangerous goods is still single, meanwhile, the transportation cost is higher, the safety operation and management difficulty is higher, the freight volume of dangerous goods transportation is reduced in recent years, the integrated process of coastal refining and capacity of China is benefited, the water way loading and unloading transportation of dangerous goods is gradually increased in recent years, and the water way loading and unloading transportation of dangerous goods is increased from 18% in 2018 to 23% in 2020.
With the development of port transportation industry, the surrounding areas of the port transportation industry gradually form densely populated areas such as businesses, houses and the like, and once accidents happen to dangerous goods involved in port cargo handling, serious injuries can be caused to the densely populated areas. Management of automated handling safety issues for goods is becoming increasingly important. At present, standard research results aiming at dangerous goods loading and unloading safety test methods are mostly applied to non-automatic loading and unloading operation, so that the research problem of the dangerous goods automatic loading and unloading safety test methods is needed to be solved.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the application and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description of the application and in the title of the application, which may not be used to limit the scope of the application.
The present application has been made in view of the above-described problems occurring in the prior art.
Therefore, the application provides a machine learning-based dangerous cargo automatic loading and unloading safety test method, which can solve the problem that the traditional free surface related multiple suppression method cannot adapt to seismic data acquired in a submarine node observation mode.
In order to solve the technical problems, the application provides a dangerous goods automatic loading and unloading safety test method based on machine learning, which comprises the following steps:
collecting related data of automatic loading and unloading of dangerous goods, and preprocessing the data;
constructing a linear regression algorithm model of machine learning according to the preprocessed parameters, and training and testing the data of the input model correspondingly;
outputting the trained and tested results, and applying the results to actual production processes.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the automatic loading and unloading related data of the dangerous goods comprise the goods of the dangerous goods, the total amount of the materials of the dangerous goods, special properties of the dangerous goods, the loading and unloading distance of the dangerous goods, the loading and unloading scene of the dangerous goods, the loading and unloading time of the dangerous goods and the loading and unloading operation of the dangerous goods.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the preprocessing comprises classifying and integrating data, and dividing the data into a sample data set and a characteristic data set according to actual production activities.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the constructing a machine-learned linear regression algorithm model includes,
fitting planar function of linear regression:
wherein h is θ Represents a fitting plane function with respect to θ, n represents a sample number, θ i Representing data parameters, x i Representing characteristic data, θ T Representing a matrix of data parameters and X representing a feature matrix.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the linear regression algorithm model includes, for each sample
y (i) =θ T x (i) +ε (i)
Wherein y is (i) Representing the true value, θ, of sample i T x (i) Representing the predicted value, ε, of sample i (i) Representing the error value of sample i.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the linear regression algorithm model also comprises the following function expression because the error is subjected to Gaussian distribution:
the calculation formula of the true value of the sample is deformed and substituted into p (epsilon) (i) ) In the formula, we get:
wherein the physical meaning of each variable is the same as defined in the foregoing formula.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the linear regression algorithm model also includes the following expression for likelihood functions for θ:
obtaining a log-likelihood function from the likelihood function:
where m represents the total number of samples, and the physical meaning of the other variables is the same as the definition in the foregoing formula.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the linear regression algorithm model also includes, assuming the parameter theta objective function as,
introducing a gradient descent strategy, wherein the gradient descent objective function is as follows:
small batch gradient descent:
wherein θ 0 Bias term, θ, representing parameter j Representing the column data parameters of the j-th column,data representing sample i, j-th column, alpha represents learning rate, i.e. step size, θ j ' represents the j-th column data parameter that goes through the gradient descent, and k represents the sample number.
The small batch gradient descent is an optimization algorithm of a linear regression algorithm introduced by combining the actual condition of the automatic loading and unloading safety test of dangerous goods, namely, a small part of data is selected for iterative calculation each time, and meanwhile, analysis is carried out by combining a settlement result and the actual condition, so that the smaller the numerical value of the learning rate is, the better the numerical value is.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: said applying the result to the actual production process includes,
calculating parameter values of the characteristic data through linear regression, and dividing the importance of the characteristic data according to the magnitude of the parameter values, namely, the higher the specific gravity of the parameter values is, the higher the priority is;
when the parameter value is greater than or equal to the average parameter value, the priority is I1, namely the data corresponding to the parameter value is the highest priority, the characteristic data corresponding to the parameter is defined as key operation data, secondary verification is needed to be carried out on the data before any operation is executed, if the secondary verification is correct, the operation safety level is judged to be T1, the data subjected to the secondary verification is transcribed and archived, the data cannot be directly modified under the condition that the data is not authorized by a main system, and meanwhile, the key operation data can be directly used for modifying the automatic loading and unloading safety strategy of dangerous goods;
if the secondary verification is abnormal, judging that the operation safety level is T2, transmitting an abnormal alarm signal to a system main station, locking all relevant operation equipment by a main system, simultaneously authorizing a main station worker to locate, troubleshoot and test the fault, ensuring that the worker transmits an operation instruction to a dispatching station after the fault is completely removed, releasing the locking state of the relevant operation equipment after the worker is authorized by the main system, carrying out normal operation, and archiving fault data and fault reasons so as to facilitate the normal operation of the follow-up verification.
The automatic loading and unloading safety test method for dangerous goods based on machine learning, disclosed by the application, comprises the following steps of: the application of the results to the actual production process also includes,
when the parameter value is smaller than the average parameter value, the priority is I2, namely the data corresponding to the parameter value is the next-level priority, the characteristic data corresponding to the parameter is defined as non-key operation data, normal verification is required to be carried out on the data before any operation is carried out, if the secondary verification is correct, the operation safety level is judged to be D1, the data subjected to the secondary verification is transcribed and archived, the data can be modified under the three-party authorization of a dispatching station, a master station staff and an operation ticket, and meanwhile, the non-key operation data cannot directly modify the automatic loading and unloading safety strategy of dangerous goods;
if the normal verification fails, the operation safety level is judged to be D2, an abnormal transmission signal is required to be sent to a system master station, the master system pauses the corresponding operation of the data, meanwhile, the data and the related data are subjected to large-scale investigation, after the problem of the fault is solved, fault values, fault points and fault reasons are recorded in the records, meanwhile, the pause operation instruction is released, and the system equipment continues to execute the normal operation.
The application has the beneficial effects that: according to the method, the machine learning is adopted to obtain the linear regression algorithm model for the automatic loading and unloading safety test of the dangerous goods, the model shows that the optimization operation of the automatic loading and unloading of the dangerous goods can be realized through the optimization algorithm of the machine learning, so that the safety of the loading and unloading of the dangerous goods is improved, and the working efficiency is improved through the optimization operation method and related data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a schematic flow chart of a method for automated handling safety testing of dangerous goods based on machine learning according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a data testing method for automated handling safety test of dangerous goods based on machine learning according to an embodiment of the present application;
fig. 3 is a schematic plan view of a fitting plan view of a machine learning-based method for automated loading and unloading safety testing of dangerous goods according to an embodiment of the present application.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present application can be understood in detail, a more particular description of the application, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, but the present application may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present application is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present application have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the application. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present application, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present application and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1, a first embodiment of the present application provides a machine learning-based method for automated loading and unloading safety testing of dangerous goods, which includes:
s1: collecting related data of automatic loading and unloading of dangerous goods, and preprocessing the data;
further, the data related to the automatic loading and unloading of the dangerous goods comprise the goods of the dangerous goods, the total amount of the materials of the dangerous goods, the special properties of the dangerous goods, the loading and unloading distance of the dangerous goods, the loading and unloading scene of the dangerous goods, the loading and unloading time of the dangerous goods and the loading and unloading operation of the dangerous goods.
It should be noted that the preprocessing includes performing a sort integration process on the data, and dividing the data into a sample data set and a feature data set according to actual production activities.
S2: constructing a linear regression algorithm model of machine learning according to the preprocessed parameters, and training and testing the data of the input model correspondingly;
still further, the constructing a machine-learned linear regression algorithm model includes,
fitting planar function of linear regression:
wherein h is θ Represents a fitting plane function with respect to θ, n represents a sample number, θ i Representing data parameters, x i Representing characteristic data, θ T Representing a matrix of data parameters and X representing a feature matrix.
It should be noted that the linear regression algorithm model includes, for each sample
y (i) =θ T x (i) +ε (i)
Wherein y is (i) Representing the true value, θ, of sample i T x (i) Representing the predicted value, ε, of sample i (i) Representing the error value of sample i.
Further, the linear regression algorithm model further includes, since the error follows a gaussian distribution, the functional expression is as follows:
the calculation formula of the true value of the sample is deformed and substituted into p (epsilon) (i) ) In the formula, we get:
wherein the physical meaning of each variable is the same as defined in the foregoing formula.
It should be noted that the linear regression algorithm model also includes the following expression for likelihood functions with respect to θ:
obtaining a log-likelihood function from the likelihood function:
where m represents the mth sample, and the physical meaning of the other variables is the same as the definition in the foregoing formula.
Further, the linear regression algorithm model also comprises the steps of setting the parameter theta objective function as,
introducing a gradient descent strategy, wherein the gradient descent objective function is as follows:
small batch gradient descent:
wherein θ 0 Bias term, θ, representing parameter j Representing the column data parameters of the j-th column,data representing sample i, j-th column, alpha represents learning rate, i.e. step size, θ j ' represents the j-th column data parameter that goes through the gradient descent, and k represents the sample number.
It should be noted that the small-batch gradient descent is an optimization algorithm of a linear regression algorithm introduced in combination with the actual condition of the automatic loading and unloading safety test of dangerous goods, that is, a small part of data is selected for iterative calculation each time, and meanwhile, analysis is performed by combining the settlement result and the actual condition, so that the smaller the numerical value of the learning rate is, the better the numerical value is found.
S3: outputting the trained and tested results, and applying the results to actual production processes.
Further, the application of the results to the actual production process includes,
calculating parameter values of the characteristic data through linear regression, and dividing the importance of the characteristic data according to the magnitude of the parameter values, namely, the higher the specific gravity of the parameter values is, the higher the priority is;
when the parameter value is greater than or equal to the average parameter value, the priority is I1, namely the data corresponding to the parameter value is the highest priority, the characteristic data corresponding to the parameter is defined as key operation data, secondary verification is needed to be carried out on the data before any operation is executed, if the secondary verification is correct, the operation safety level is judged to be T1, the data subjected to the secondary verification is transcribed and archived, the data cannot be directly modified under the condition that the data is not authorized by a main system, and meanwhile, the key operation data can be directly used for modifying the automatic loading and unloading safety strategy of dangerous goods;
if the secondary verification is abnormal, judging that the operation safety level is T2, transmitting an abnormal alarm signal to a system main station, locking all relevant operation equipment by a main system, simultaneously authorizing a main station worker to locate, troubleshoot and test the fault, ensuring that the worker transmits an operation instruction to a dispatching station after the fault is completely removed, releasing the locking state of the relevant operation equipment after the worker is authorized by the main system, carrying out normal operation, and archiving fault data and fault reasons so as to facilitate the normal operation of the follow-up verification.
Further, the application of the result to the actual production process also comprises,
when the parameter value is smaller than the average parameter value, the priority is I2, namely the data corresponding to the parameter value is the next-level priority, the characteristic data corresponding to the parameter is defined as non-key operation data, normal verification is required to be carried out on the data before any operation is carried out, if the secondary verification is correct, the operation safety level is judged to be D1, the data subjected to the secondary verification is transcribed and archived, the data can be modified under the three-party authorization of a dispatching station, a master station staff and an operation ticket, and meanwhile, the non-key operation data cannot directly modify the automatic loading and unloading safety strategy of dangerous goods;
if the normal verification fails, the operation safety level is judged to be D2, an abnormal transmission signal is required to be sent to a system master station, the master system pauses the corresponding operation of the data, meanwhile, the data and the related data are subjected to large-scale investigation, after the problem of the fault is solved, fault values, fault points and fault reasons are recorded in the records, meanwhile, the pause operation instruction is released, and the system equipment continues to execute the normal operation.
Example 2
Referring to fig. 2-3, for one embodiment of the present application, a machine learning-based method for automated handling safety testing of dangerous goods is provided, and in order to verify the beneficial effects of the present application, scientific demonstration is performed through experiments.
The present embodiment will be described by taking a 10-ten thousand-ton container terminal constructed in a harbor area as an example. The average carrying capacity of each ship is 2000 cases of the whole ship dangerous goods transportation capacity accounting for 5% of the whole ship, and the factors simulating the accidents of the tank container caused by the fact that dangerous goods are propylene and liquid ammonia are many, such as the integrity of the container body, the packaging process, the temperature, the humidity, jolt and the like, and the emergency test and the prediction are carried out on the automatic loading and unloading safety of dangerous goods by combining with the local main wind direction.
Fig. 2 is a fitting plane obtained in the training process of the experimental method, and the linear regression algorithm of the automatic loading and unloading safety test of the dangerous goods constructed by the method is developed based on the fitting plane.
Fig. 3 shows a data testing schematic diagram of the present application, specifically, a data testing schematic diagram of a certain sample and its related parameters, wherein the abscissa of the diagram is a data parameter, and the ordinate is a test variable. Meanwhile, the coincidence of independent identical distribution among samples and sample parameters is a necessary premise for carrying out linear regression algorithm training and testing, the sample data are key influence factors, and the data parameters are regarded as specific gravity of the key influence factors and are calculated according to the specific gravity.
When the learning rate is 0.001, the partial data and data parameters are shown in the following table:
1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | |
θ i | 0.00 | 0.12 | 0.30 | 0.45 | 0.51 | 0.82 | 1.00 | 1.25 |
x i | 1.23 | 3.01 | 3.79 | 3.40 | 4.21 | 5.34 | 4.23 | 6.63 |
the application relates to a machine learning-based automatic loading and unloading safety test technology for dangerous goods, which is mainly used for maximally avoiding unexpected situations which are extremely easy to occur in the automatic loading and unloading process of dangerous goods. The method comprises the steps of firstly collecting related data of automatic loading and unloading of dangerous goods, preprocessing the data, constructing a linear regression algorithm model of machine learning according to the preprocessed parameters, training and testing the data of an input model correspondingly, outputting a result which passes the training and testing, and applying the result to an actual production process.
It should be noted that the above embodiments are only for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application may be modified or substituted without departing from the spirit and scope of the technical solution of the present application, which is intended to be covered in the scope of the claims of the present application.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be realized by adopting various computer languages, such as object-oriented programming language Java, an transliteration script language JavaScript and the like.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (7)
1. The automatic loading and unloading safety test method for dangerous goods based on machine learning is characterized by comprising the following steps of: comprising the steps of (a) a step of,
collecting related data of automatic loading and unloading of dangerous goods, and preprocessing the data;
constructing a linear regression algorithm model of machine learning according to the preprocessed parameters, and training and testing the data of the input model correspondingly;
outputting a trained and tested result, and applying the result to an actual production process;
the automatic loading and unloading related data of the dangerous goods comprise the goods of the dangerous goods, the total amount of the materials of the dangerous goods, the special properties of the dangerous goods, the loading and unloading distance of the dangerous goods, the loading and unloading scene of the dangerous goods, the loading and unloading time of the dangerous goods and the loading and unloading operation of the dangerous goods;
the preprocessing comprises the steps of classifying and integrating data, and dividing the data into a sample data set and a characteristic data set according to actual production activities;
the constructing a machine-learned linear regression algorithm model includes,
fitting planar function of linear regression:
wherein,representation about->Fitting a plane function +_>Representing sample number, ++>Representing data parameters->Representing characteristic data, < >>Representing a matrix of data parameters>Representing the feature matrix.
2. The machine learning-based dangerous cargo automatic loading and unloading safety test method as defined in claim 1, wherein: the linear regression algorithm model includes, for each sample:
wherein,representing the true value of sample i, +.>Representing the predictive value of sample i +.>Representing the error value of sample i.
3. The machine learning-based dangerous cargo automatic loading and unloading safety test method as defined in claim 2, wherein: the linear regression algorithm model also comprises the following function expression because the error is subjected to Gaussian distribution:
substituting the deformed sample true value calculation formula into the sample true value calculation formulaIn the formula, we get:
wherein the physical meaning of each variable is the same as defined in the foregoing formula.
4. A machine learning based method of automated safety testing of loading and unloading of hazardous materials as set forth in claim 3, wherein: the linear regression algorithm model also includes, in terms ofThe expression of likelihood function of (c) is as follows:
obtaining a log-likelihood function from the likelihood function:
wherein,representing the mth sample, the physical meaning of the other variables is the same as the definition in the preceding formula.
5. The machine learning-based dangerous cargo automatic loading and unloading safety test method as defined in claim 4, wherein: the linear regression algorithm model also comprises setting parametersThe objective function is that the function of the object is,
introducing a gradient descent strategy, wherein the gradient descent objective function is as follows:
small batch gradient descent:
wherein,bias term representing parameter->Represents the j-th column data parameter,>data representing sample i, j-th column,>representing learning rate, i.e. step size,/->Column j data parameters representing the gradient descent, < +.>Representing the sample number;
the small batch gradient descent is an optimization algorithm of a linear regression algorithm introduced by combining the actual condition of the automatic loading and unloading safety test of dangerous goods, namely, a small part of data is selected for iterative calculation each time, and meanwhile, analysis is carried out by combining a settlement result and the actual condition, so that the smaller the numerical value of the learning rate is, the better the numerical value is.
6. The machine learning-based dangerous cargo automatic loading and unloading safety test method as defined in claim 5, wherein: the application of the results to the actual production process includes,
calculating parameter values of the characteristic data through linear regression, and dividing the importance of the characteristic data according to the magnitude of the parameter values, namely, the higher the specific gravity of the parameter values is, the higher the priority is;
when the parameter value is greater than or equal to the average parameter value, the priority is I1, namely the data corresponding to the parameter value is the highest priority, the characteristic data corresponding to the parameter is defined as key operation data, secondary verification is needed to be carried out on the data before any operation is executed, if the secondary verification is correct, the operation safety level is judged to be T1, the data subjected to the secondary verification is transcribed and archived, the data cannot be directly modified under the condition that the data is not authorized by a main system, and meanwhile, the key operation data can be directly used for modifying the automatic loading and unloading safety strategy of dangerous goods;
if the secondary verification is abnormal, judging that the operation safety level is T2, transmitting an abnormal alarm signal to a system main station, locking all relevant operation equipment by a main system, simultaneously authorizing a main station worker to locate, troubleshoot and test the fault, ensuring that the worker transmits an operation instruction to a dispatching station after the fault is completely removed, releasing the locking state of the relevant operation equipment after the worker is authorized by the main system, carrying out normal operation, and archiving fault data and fault reasons so as to facilitate the normal operation of the follow-up verification.
7. The machine learning-based dangerous cargo automatic loading and unloading safety test method as defined in claim 6, wherein: the application of the results to the actual production process also includes,
when the parameter value is smaller than the average parameter value, the priority is I2, namely the data corresponding to the parameter value is the next-level priority, the characteristic data corresponding to the parameter is defined as non-key operation data, normal verification is required to be carried out on the data before any operation is carried out, if the secondary verification is correct, the operation safety level is judged to be D1, the data subjected to the secondary verification is transcribed and archived, the data can be modified under the three-party authorization of a dispatching station, a master station staff and an operation ticket, and meanwhile, the non-key operation data cannot directly modify the automatic loading and unloading safety strategy of dangerous goods;
if the normal verification fails, the operation safety level is judged to be D2, an abnormal transmission signal is required to be sent to a system master station, the master system pauses the corresponding operation of the data, meanwhile, the data and the related data are subjected to large-scale investigation, after the problem of the fault is solved, fault values, fault points and fault reasons are recorded in the records, meanwhile, the pause operation instruction is released, and the system equipment continues to execute the normal operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310067758.6A CN116308003B (en) | 2023-02-06 | 2023-02-06 | Dangerous goods automatic loading and unloading safety test method based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310067758.6A CN116308003B (en) | 2023-02-06 | 2023-02-06 | Dangerous goods automatic loading and unloading safety test method based on machine learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116308003A CN116308003A (en) | 2023-06-23 |
CN116308003B true CN116308003B (en) | 2023-11-17 |
Family
ID=86795039
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310067758.6A Active CN116308003B (en) | 2023-02-06 | 2023-02-06 | Dangerous goods automatic loading and unloading safety test method based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116308003B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117557109B (en) * | 2024-01-11 | 2024-04-05 | 交通运输部水运科学研究所 | Fusion collaborative operation method and system of ship digital physical infrastructure |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108347764A (en) * | 2018-01-23 | 2018-07-31 | 南京航空航天大学 | Examination hall radio cheating signal framing method and system based on deep learning |
CN111460382A (en) * | 2020-03-30 | 2020-07-28 | 上海交通大学 | Fuel vehicle harmful gas emission prediction method and system based on Gaussian process regression |
CN112183979A (en) * | 2020-09-18 | 2021-01-05 | 浙江省安全生产科学研究院 | Hazardous chemical substance loading and unloading safety risk assessment method based on multi-source information fusion |
US11151419B1 (en) * | 2021-04-09 | 2021-10-19 | WARPSPEED, Inc. | Data segmentation using machine learning |
CN114743073A (en) * | 2022-06-13 | 2022-07-12 | 交通运输部水运科学研究所 | Dangerous cargo container early warning method and device based on deep learning |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160063380A1 (en) * | 2014-08-26 | 2016-03-03 | International Business Machines Corporation | Quantifying and predicting herding effects in collective rating systems |
-
2023
- 2023-02-06 CN CN202310067758.6A patent/CN116308003B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108347764A (en) * | 2018-01-23 | 2018-07-31 | 南京航空航天大学 | Examination hall radio cheating signal framing method and system based on deep learning |
CN111460382A (en) * | 2020-03-30 | 2020-07-28 | 上海交通大学 | Fuel vehicle harmful gas emission prediction method and system based on Gaussian process regression |
CN112183979A (en) * | 2020-09-18 | 2021-01-05 | 浙江省安全生产科学研究院 | Hazardous chemical substance loading and unloading safety risk assessment method based on multi-source information fusion |
US11151419B1 (en) * | 2021-04-09 | 2021-10-19 | WARPSPEED, Inc. | Data segmentation using machine learning |
CN114743073A (en) * | 2022-06-13 | 2022-07-12 | 交通运输部水运科学研究所 | Dangerous cargo container early warning method and device based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN116308003A (en) | 2023-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116308003B (en) | Dangerous goods automatic loading and unloading safety test method based on machine learning | |
CN104915779A (en) | Sampling test design method based on Bayesian network | |
She et al. | Diagnosis and prediction for loss of coolant accidents in nuclear power plants using deep learning methods | |
CN107272667A (en) | A kind of industrial process fault detection method based on parallel PLS | |
CN106483942A (en) | The intelligence control system of a kind of semiconductor manufacturing facility and technique and method | |
CN109034140A (en) | Industrial control network abnormal signal detection method based on deep learning structure | |
CN116994418B (en) | Pipeline safety early warning method and system | |
CN112507608A (en) | Security simulation method and device for space human-computer interaction system | |
CN112465001A (en) | Classification method and device based on logistic regression | |
CN111736636A (en) | Flooded waterwheel room early warning method and system based on knowledge graph | |
CN111062827B (en) | Engineering supervision method based on artificial intelligence mode | |
KR102399597B1 (en) | Intelligent safety analysis technology using AI | |
KR102418796B1 (en) | FMEA failure mode recommend system | |
CN116485032A (en) | Aviation product processing quality prediction method considering multidimensional influence factors | |
CN112819262A (en) | Memory, process pipeline inspection and maintenance decision method, device and equipment | |
CN116541748A (en) | Power grid fault diagnosis method and system based on artificial intelligence technology | |
CN112309063B (en) | Method and device for extracting hybrid fiber intrusion signal feature spectrum | |
Kim et al. | SIGNAL FAULT IDENTIFICATION IN NUCLEAR POWER PLANTS BASED ON DEEP NEURAL NETWORKS. | |
CN114139853A (en) | Steel structure product list processing method and device based on big data | |
He et al. | Model for unanticipated fault detection by ocpca | |
Feiveson et al. | Reliability of space-shuttle pressure vessels with random batch effects | |
CN113865681A (en) | Intelligent material weighing method and system | |
CN117010861A (en) | Nuclear power plant pre-service in-service inspection making method, system, storage medium and terminal | |
CN113378294B (en) | Safety inward bound design feasibility inspection device and inspection method | |
CN110879821A (en) | Method, device, equipment and storage medium for generating rating card model derivative label |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |