Coal mine safety production analysis method and system fusing multi-modal data

Abstract

The application relates to a coal mine safety production analysis method and system fusing multi-modal data, relates to the technical field of mining management, and comprises the following steps: calibrating a device aging label based on a device state account; classifying personnel behavior data with a service length less than or equal to a threshold value to determine a first, a second and a third type of violation behavior; randomly configuring a coal mine production quantity; traversing the first, the second and the third type of violation behavior, combining the production quantity and the device aging label to construct an index constraint, searching a corresponding coal mine production scheduling sample set, and calculating a first, a second and a third coal mine production accident triggering probability; and when the first, the second and the third coal mine production accident triggering probability are all less than or equal to a threshold value, scheduling management is performed according to the coal mine production quantity. The application solves the problem that traditional coal mine scheduling management only makes decisions from a single dimension, fails to consider the multidimensional collaborative demand of production efficiency and operation safety, and thus lacks precise matching and is insufficient in delicacy, and cannot realize comprehensive management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mining management, in particular to a coal mine safety production analysis method and system fusing multi-modal data. BACKGROUND

[0002] With the development of coal mine production technology, coal mine production management optimization has become a key foundation to ensure production safety and improve efficiency. The existing coal mine production management mode only makes decisions from a single dimension, either increasing safety risks due to neglecting equipment status, or causing insufficient production coordination due to neglecting personnel behavior, which is difficult to balance the multi-dimensional needs of production efficiency and operation safety, and cannot meet the actual requirements of improving the fineness of coal mine production management. SUMMARY

[0003] To solve the above technical problems, the present application provides a coal mine safety production analysis method and system fusing multi-modal data, which improves the satisfaction of multi-dimensional needs and the fineness of coal mine production management, changes the traditional single dimension mode, realizes the balance of operation safety and production efficiency, and effectively improves the comprehensiveness of mining production management.

[0004] The present application embodiment discloses the following technical scheme:

[0005] In a first aspect, the present application embodiment provides a coal mine safety production analysis method fusing multi-modal data, which comprises:

[0006] Based on the pre-stored equipment status account book, the equipment aging label is calibrated;

[0007] Classify personnel behavior data with a service length less than or equal to a service length threshold to determine a first type of violation behavior, a second type of violation behavior, and a third type of violation behavior. The first type of violation behavior represents a violation behavior type with a safety event trigger probability greater than or equal to a trigger probability threshold. The second type of violation behavior represents a violation behavior type with a safety event trigger probability less than the trigger probability threshold and greater than 0. The third type of violation behavior represents a violation behavior that is inconsistent with the standard behavior and has a safety event trigger probability of 0.

[0008] Randomly configure a coal mine production quantity;

[0009] Iterate through the first type of violation behavior, the second type of violation behavior, and the third type of violation behavior, respectively combine with the coal mine production quantity and the equipment aging label to construct index constraints, retrieve a first type of coal mine production sample set, a second type of coal mine production sample set, and a third type of coal mine production sample set, respectively calculate the accident sample proportion, and obtain a first type of coal mine production accident trigger probability, a second type of coal mine production accident trigger probability, and a third type of coal mine production accident trigger probability;

[0010] When the triggering probability of a type of coal mine production accident, the triggering probability of a type of coal mine production accident and the triggering probability of a type of coal mine production accident are less than or equal to the accident triggering probability threshold, production scheduling management is performed according to the coal mine production quantity.

[0011] In a second aspect, the embodiments of the present application provide a coal mine safety production analysis system fusing multi-modal data, the system comprises:

[0012] The device aging calibration module is configured to calibrate a device aging label based on a pre-stored device state account book.

[0013] The personnel violation classification module is configured to classify personnel behavior data with a service length less than or equal to a service length threshold, and determine a type of violation behavior, a type of violation behavior and a type of violation behavior, wherein the type of violation behavior represents a type of violation behavior with a safety event triggering probability greater than or equal to a triggering probability threshold, the type of violation behavior represents a type of violation behavior with a safety event triggering probability less than the triggering probability threshold and greater than 0, and the type of violation behavior represents a type of violation behavior inconsistent with a standard behavior and with a safety event triggering probability equal to 0.

[0014] The random configuration production module is configured to randomly configure a coal mine production quantity.

[0015] The accident probability calculation module is configured to traverse the type of violation behavior, the type of violation behavior and the type of violation behavior, combine with the coal mine production quantity and the device aging label respectively to construct index constraints, retrieve a type of coal mine production scheduling sample set, a type of coal mine production scheduling sample set and a type of coal mine production scheduling sample set, respectively perform accident sample proportion calculation, and obtain a type of coal mine production accident triggering probability, a type of coal mine production accident triggering probability and a type of coal mine production accident triggering probability.

[0016] The production scheduling management module is configured to perform production scheduling management according to the coal mine production quantity when the triggering probability of a type of coal mine production accident, the triggering probability of a type of coal mine production accident and the triggering probability of a type of coal mine production accident are less than or equal to the accident triggering probability threshold.

[0017] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0018] The application provides a coal mine safety production analysis method and system fusing multi-modal data. Through device aging label calibration, personnel violation behavior classification, production capacity configuration, accident probability calculation and collaborative operation of production scheduling management, safe and efficient control of coal mine production scheduling is realized. First, based on the device state account, the service time and maintenance frequency of each device are extracted, the stable probability of the corresponding type is predicted through the channel to generate a stable probability, and the stable probability is integrated into a device aging label. The service time of the personnel behavior data meets the threshold, and the personnel behavior data is classified into three categories (safety event trigger probability >= threshold), two categories (probability < threshold and > 0) and three categories (probability = 0) of violation behaviors. After randomly configuring the coal mine production capacity, the index constraint is constructed in combination with the former two, the first, second and third coal mine production scheduling sample sets are retrieved, the accident sample proportion calculation is performed, and the three types of accident trigger probabilities are obtained. Finally, according to whether the probability meets the standard, the production scheduling management is executed or the production capacity is adjusted according to the preset gradient, the risk is prompted on the user side, and a whole-process closed-loop management is formed.

[0019] The technical scheme of the application fuses multi-modal data to construct a "production-equipment-personnel" three-dimensional management system, solves the problem that the traditional coal mine production scheduling management only makes decisions from a single dimension, and cannot balance the multi-dimensional demand of production efficiency and operation safety, and the problem of poor precision of production scheduling management. Through device risk quantification, hierarchical violation control and dynamic production capacity adjustment, accurate basis is provided for balancing safety and production capacity, and the comprehensiveness of mining production management is effectively improved by taking into account production and operation safety. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creating any inventive labor.

[0021] Figure 1 The flowchart of the coal mine safety production analysis method fusing multi-modal data provided by the embodiment of the application;

[0022] Figure 2 The structure diagram of the coal mine safety production analysis system fusing multi-modal data provided by the embodiment of the application.

[0023] In the drawings, the components represented by the numbers are described as follows:

[0024] The device aging calibration module 01, the personnel violation classification module 02, the random production capacity configuration module 03, the accident probability calculation module 04 and the production scheduling management module 05. DETAILED DESCRIPTION

[0025] The application provides a coal mine safety production analysis method and system fusing multi-modal data, and aims to solve the technical problem that the coal mine production scheduling management only considers a single dimension, cannot consider multi-dimensional requirements such as production efficiency, equipment state and personnel behavior, leads to poor scheduling management precision, and it is difficult to realize production and operation safety planning.

[0026] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person skilled in the art without creative work fall within the protection scope of the application.

[0027] In the description of the application, the terms "first", "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined as "first", "second" can explicitly or implicitly include one or more of the features. In the description of the application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0028] In the description of the application, the term "for example" is used to indicate "as an example, illustration or explanation". Any embodiment described as "for example" in the application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the application. In the following description, details are listed for the purpose of explanation. It should be understood that a person skilled in the art can realize the application without using these specific details. In other examples, well-known structures and processes will not be described in detail to avoid unnecessary details making the description of the application obscure. Therefore, the application is not intended to be limited to the shown embodiments, but is consistent with the broadest scope of principles and features disclosed in the application.

[0029] Embodiment one, as shown in the accompanying Figure 1 The application provides a coal mine safety production analysis method fusing multi-modal data, which comprises the following steps:

[0030] S110: based on the pre-stored equipment state account, calibrate the equipment aging label;

[0031] In the embodiment of the application, in the equipment aging label calibration stage, in order to ensure that the label can accurately reflect the accident risk of each device, the comprehensive risk identification is formed through the equipment state data extraction and model exclusive channel processing.

[0032] Specifically, first, the service length and the maintenance frequency of the first number equipment of the coal mine production line are extracted from the pre-stored equipment state account as basic characteristic parameters, processed through the first operation stability probability prediction channel bound with the equipment model, and the first number equipment stability probability (i.e., the probability of accidents occurring when the equipment is operating) is generated.

[0033] Further, the same operation is performed on the Qth number equipment of the coal mine production line until the service length and the maintenance frequency of all number equipment are extracted, and the corresponding equipment stability probability is generated through the exclusive operation stability probability prediction channel bound with the respective model.

[0034] Finally, the stability probabilities of the first number equipment to the Qth number equipment are integrated to form the equipment aging label. The label integrates the stability probabilities of all number equipment of the coal mine production line and reflects the degradation trend and risk state of each equipment.

[0035] This step realizes the quantification and integration of equipment accident risk by extracting key state parameters one by one according to the equipment number and generating stability probability by matching the model exclusive probability prediction channel, providing accurate equipment dimension basic data support for subsequent production risk assessment combined with personnel behavior data and production capacity.

[0036] The step S110 in the method provided in the embodiment of the present application includes:

[0037] The service length and the maintenance frequency of the first number equipment of the coal mine production line are extracted from the equipment state account, processed through the first operation stability probability prediction channel bound with the first number equipment model, and the first number equipment stability probability is generated, wherein the equipment stability probability represents the probability of accidents occurring when the equipment is operating;

[0038] The service length and the maintenance frequency of the Qth number equipment of the coal mine production line are extracted from the equipment state account, processed through the Qth operation stability probability prediction channel bound with the Qth number equipment model, and the Qth number equipment stability probability is generated;

[0039] The first number equipment stability probability to the Qth number equipment stability probability is added to the equipment aging label.

[0040] In the embodiment of the present application, in the scenario where the coal mine production line contains multiple number equipment and each equipment model, state parameter and risk characteristic are different, in order to ensure that the label can comprehensively and accurately reflect the risk state of all equipment of the coal mine production line, the stability probability of each number equipment is generated and integrated to realize the quantitative representation of the whole production line equipment risk.

[0041] In the method provided by the embodiments of the present application, the step of "extracting the service duration of the first number equipment of the coal production line and the maintenance frequency of the first number equipment from the device state account, and generating the stable probability of the first number equipment through the first operation stable probability prediction channel bound with the first number equipment model" comprises:

[0042] searching a plurality of first number equipment model operation record data, wherein any one of the plurality of first number equipment model operation record data comprises first number equipment service duration record data, first number equipment maintenance frequency record data and equipment failure trigger identifier, when the identifier is equal to 1, it is considered as triggering the equipment failure state, and when the identifier is equal to 0, it is considered as triggering the equipment health operation state;

[0043] traversing the plurality of first number equipment model operation record data, and searching a plurality of supplementary equipment failure trigger identifiers of the first number equipment model with the first number equipment service duration record data and the first number equipment maintenance frequency record data as constraints;

[0044] counting the proportion of the number of 0 values in the plurality of supplementary equipment failure trigger identifiers and the equipment failure trigger identifier, and setting it as a label for identifying the stable probability of the first number equipment;

[0045] taking the label for identifying the stable probability of the first number equipment as supervision, taking the first number equipment service duration record data and the first number equipment maintenance frequency record data as input, calling the plurality of first number equipment model operation record data, and training the first operation stable probability prediction channel through machine learning, and binding the first number equipment model.

[0046] In the model training stage of the generation of the equipment stable probability in the embodiments of the present application, in order to ensure that the trained first operation stable probability prediction channel can accurately adapt to the characteristics of the first number equipment model, a device-specific prediction channel needs to be constructed through historical operation data retrieval and supervised learning.

[0047] Specifically, first, a plurality of operation record data of the first number equipment model are retrieved from the database, which contain state parameters such as service duration, maintenance frequency, and trigger identifiers (1 for failure and 0 for health) for identifying whether the equipment is faulty, providing basic samples for model training.

[0048] Among them, by traversing the historical data and retrieving the supplementary failure identifier with the service duration and the maintenance frequency as constraints, the sample dimension can be enriched to ensure the comprehensiveness of the training data.

[0049] Further, the number of health job states (i.e., identified as 0) is used as a stability probability label, and the state parameters are used as input for machine learning training, so that the model can accurately map the correlation between device state and accident probability, and finally form a device-specific prediction channel bound to the device model.

[0050] In the embodiments of the present application, when training the first job stability probability prediction channel, multi-source sample fusion, probability label calibration and supervised learning training are required to achieve accurate mapping of device state and stability probability, providing reliable model support for subsequent generation of device aging labels.

[0051] Specifically, taking the first serial number device model as an example, first, collect historical job records containing service life, maintenance frequency and fault trigger identification, and supplement samples by searching under the same state parameters to expand the training data volume.

[0052] For example, if the service life of a device is 5000 hours, the maintenance frequency is 2 times per month, and the trigger identification is 0 (healthy), search for other records under the same parameter combination as supplementary samples, and if 8 out of 10 supplementary samples are identified as 0, the stability probability label under this state is 80%.

[0053] Further, using the stability probability label as a supervision target, the service life and maintenance frequency are used as input features, and the model is trained by a random forest algorithm, so that the model can output the stability probability according to the real-time state parameters.

[0054] Specifically, first, divide the collected multiple job record data of the first serial number device model into training set, validation set and test set in the ratio of 8:1:1, to ensure that the data covers different service life, maintenance frequency and fault trigger identification scenarios, to reflect the job characteristics of the device model under diversification.

[0055] For example, 1600 training sets, 200 validation sets and 200 test sets are extracted from 2000 records for parameter learning, performance evaluation and generalization ability testing of the model, to ensure that the trained model can adapt to the state characteristics of the first serial number device model under different service life and maintenance frequency.

[0056] Further, when training the random forest model using the training set, 70% of the sample data is randomly selected from the training set each time, and the service life record data and maintenance frequency record data are used as input features, and the stability probability label is used as output label and input into the model.

[0057] During training, the initial number of decision trees was set at 30, and model performance was evaluated on the validation set every time five trees were added. After the first round of training, the average error between the predicted stability probability and the actual stability probability label on the validation set was 0.08. When the number of decision trees was increased to 50, this error narrowed to 0.05, indicating that the model's ability to fit the relationship between device status and stability probability is gradually improving.

[0058] To prevent overfitting, an early stopping mechanism was implemented. Training was stopped when the validation set error stopped decreasing for four consecutive rounds (error fluctuation was less than 0.002), indicating model convergence. For example, if the validation set error stabilized at 0.04 and did not decrease for four consecutive rounds during the 25th round of training, the model was considered converged and training was stopped.

[0059] Finally, the trained random forest model can receive the real-time service time and maintenance frequency of the first-number equipment and output the corresponding stability probability, providing a quantitative basis for calculating the stability probability of the first-number equipment. The model serves as the first operation stability probability prediction channel bound to the first-number equipment model.

[0060] For example, if the first-numbered piece of equipment is a coal mine roadheader, and a historical record shows a service life of 8,000 hours and a maintenance frequency of four times per month, the corresponding stability probability label is 65%. After inputting this data into model training, when the roadheader's real-time service life reaches 7,500 hours and a maintenance frequency of three times per month, the trained first-operation stability probability prediction channel processes it and outputs a stability probability of 72%. This accurately reflects the accident risk of equipment operation in this state and provides quantitative data for calibrating equipment aging labels.

[0061] Similarly, for the Q-th equipment in the coal mine production line, the same model training process as the first-number equipment is used to ensure that the Q-th operation stability probability prediction channel can accurately adapt to the characteristics of the equipment model.

[0062] Specifically, we first retrieve multiple pieces of Q-numbered equipment model operation record data from the equipment status ledger. Each record contains its service time record data, maintenance frequency record data, and equipment fault trigger flag (1 for fault, 0 for healthy).

[0063] Furthermore, by traversing these records, supplementary fault trigger identifiers are retrieved with service time and maintenance frequency as constraints, and the proportion of healthy status is calculated as a stable probability label; then, using this label as supervision and service time and maintenance frequency as input, historical data is retrieved to train the Q-th operation stable probability prediction channel through machine learning, and it is bound to the Q-th position number equipment model.

[0064] Furthermore, the stability probabilities of the devices from the first to the Qth position are sequentially integrated to form a device aging label.

[0065] For example, if the Qth device is a coal mine ventilator, and a historical record shows that the service time is 12000 hours and the maintenance frequency is 6 times per month, the corresponding stable probability label is 40%. After model training, when the real-time service time of the ventilator is 11000 hours and the maintenance frequency is 5 times per month, the stable probability predicted by the Qth operation stable probability prediction channel is 48%.

[0066] Further, the stable probability of 72% of the first number of heading machines and the stable probability of 48% of the Qth number of ventilators, and the stable probabilities of other number of devices (such as the second number of scraper conveyors 85%, the third number of hydraulic supports 60%, etc.) are integrated to form a device aging label.

[0067] The device aging label collectively presents the quantitative value of the accident risk of all production line devices, providing unified device dimension data support for subsequent combination with personnel violation behavior and coal mine production to build index constraints, and realizing systematic representation of multiple device states.

[0068] S120: classifying the personnel behavior data with a service time less than or equal to a service time threshold, to determine a first type of violation behavior, a second type of violation behavior, and a third type of violation behavior, wherein the first type of violation behavior represents a violation behavior type with a safety event trigger probability greater than or equal to a trigger probability threshold, the second type of violation behavior represents a violation behavior type with a safety event trigger probability less than the trigger probability threshold and greater than 0, and the third type of violation behavior represents a violation behavior inconsistent with a standard behavior and with a safety event trigger probability equal to 0;

[0069] In the personnel violation behavior classification stage in the embodiment of the application, to ensure that the classification result accurately reflects the safety risk level of different violation behaviors, behavior data extraction and matching with a standard action library, and historical accident correlation analysis are required to realize accurate risk classification.

[0070] Specifically, first, the first personnel behavior data containing the execution post number and the execution action are extracted from the personnel behavior data, the execution post number is matched with the pre-constructed standard action library, and the standard execution action corresponding to the post is obtained as the basis for judging the behavior compliance.

[0071] Further, when the execution action is inconsistent with the standard execution action, the historical operation records of the post number are searched with the execution action as a constraint, the proportion of transactions in the historical records triggered by the same or similar violation actions is calculated, and the safety event trigger probability of the behavior is set as the proportion.

[0072] At the same time, based on the trigger probability threshold set by the user end, the first personnel behavior data is classified.

[0073] Finally, when all personnel behavior data is completed, the classification results of the three types of violation behaviors are output, which provides accurate personnel dimension risk quantification basis for subsequent index constraints of production scheduling risk assessment combined with equipment aging labels and coal mine production.

[0074] The step S120 in the method provided by the embodiment of the application comprises:

[0075] From the personnel behavior data, first personnel behavior data is extracted, wherein the first personnel behavior data comprises an execution post number and an execution action;

[0076] Based on the execution post number, a pre-constructed standard action library is input, and a standard behavior is matched, wherein the standard behavior comprises a standard execution action;

[0077] When the execution action and the standard execution action are inconsistent, the execution post number historical work record is retrieved with the execution action as a constraint;

[0078] The safety accident triggering transaction proportion in the execution post number historical work record is counted and set as the safety event triggering probability;

[0079] Based on the trigger probability threshold value pre-set by the user end, the first personnel behavior data is classified in combination with the safety event triggering probability;

[0080] When all personnel behavior data analysis is completed, the one type of violation behavior, the two types of violation behavior and the three types of violation behavior are output.

[0081] In the embodiment of the application, in order to ensure that the classification results can accurately distinguish the safety risk levels of different violation behaviors, risk classification is realized through behavior feature extraction, standard library matching and historical accident association analysis, and personnel dimension risk basis is provided for subsequent production scheduling risk assessment.

[0082] Specifically, first, first personnel behavior data containing an execution post number and an execution action is extracted from personnel behavior data, so as to clearly define the post attribute and specific operation content of the behavior subject.

[0083] For example, if the first personnel behavior data extracted from the personnel behavior data is “execution post number 005 (coal mining machine driver post), execution action ‘not checking hydraulic system pressure to rated value before starting’”, it can be determined that the behavior subject is the coal mining machine driver post, and the specific operation content is not checking the hydraulic system pressure to the rated value before starting, which lays a foundation for subsequent matching with the standard action library.

[0084] Further, based on the execution post number, a pre-constructed standard action library is matched, and the standard execution action corresponding to the post is obtained, which is used as a criterion for judging behavior compliance.

[0085] For example, the standard action library of the coal mining machine driver position specifies that "the hydraulic system pressure needs to be checked to the rated value before starting the machine", and this action is the standard execution action of the position.

[0086] Further, when the execution action is inconsistent with the standard execution action, it is determined as a potential violation behavior, and the safety risk needs to be quantified through historical data retrieval.

[0087] At the same time, with the execution action as a constraint, the historical operation records of the same execution position number are retrieved, and the proportion of transactions in the historical records triggered by the same or similar violation actions is calculated, which is set as the safety event triggering probability.

[0088] For example, if the "hydraulic system pressure is not checked to the rated value before starting the machine" action appears 80 times in the historical records of the coal mining machine driver position, and 12 times of safety events related to hydraulic system failure are triggered, the safety event triggering probability of this action is 15% (12 / 80).

[0089] Further, based on the trigger probability threshold set by the user end (such as the threshold set to 10%), the first personnel behavior data is classified: the safety event triggering probability greater than or equal to 10% is classified as a class of violation behavior (high risk), less than 10% and greater than 0 is classified as a class of violation behavior (medium risk), and the standard behavior is inconsistent with the historical records without triggering safety accidents (triggering probability is 0) is classified as a class of violation behavior (low risk).

[0090] Finally, when all personnel behavior data is analyzed as described above, the classification results of the three types of violation behaviors are summarized and output to realize the systematic risk classification of personnel violation behaviors.

[0091] The classification process is associated with historical accident data through position-specific standard comparison, which ensures that the classification results can accurately reflect the actual risk level of different violation behaviors, and lays a foundation for subsequent construction of multi-dimensional production scheduling constraints combined with equipment aging labels and coal mine production.

[0092] S130: Randomly configure the coal mine production;

[0093] In the coal mine production quantity random configuration stage in the embodiment of the application, in order to ensure that the configuration result can cover the risk scene under different production load, the diversification of production quantity needs to be realized through unbiased random sampling and full range coverage principle, which provides comprehensive production dimension data support for subsequent multi-dimensional production scheduling risk assessment.

[0094] Specifically, first, the value range of the coal mine production is determined, which is based on the designed capacity of the coal mine production line, the maximum load of the equipment, and the production threshold defined by the safety regulations, covering the full range from the minimum safe production to the highest designed production.

[0095] For example, the designed capacity of a certain coal mine production line is 8000 tons per day, and the safety regulations define the minimum production as 3000 tons per day, so the value range of the production is set to 3000 tons to 8000 tons.

[0096] Further, random sampling method is used to generate a number of discrete production values within the above value range, ensuring that each value meets the operating load characteristics of the production equipment, and the difference between any two values is not less than the preset minimum interval (such as 500 tons), to avoid evaluation redundancy caused by too dense production.

[0097] For example, within the range of 3000 tons to 8000 tons, 3200 tons, 3800 tons, 4500 tons, 5200 tons, 6000 tons, 6800 tons, 7500 tons, and 8000 tons are randomly generated, a total of 8 production values.

[0098] Finally, the generated number of coal mine production is used as the random configuration result to form a production set. This set covers the possible production load state of the coal mine production line, providing diversified production dimension basis data for subsequent risk assessment of production scheduling combined with equipment aging labels and personnel violation behavior data.

[0099] This step realizes the comprehensive coverage of production load by determining the value range and randomly generating diversified production values, providing reliable production dimension support for multi-dimensional risk assessment, which helps to improve the adaptability and safety of the production scheduling scheme.

[0100] S140: Traverse the first type of violation behavior, the second type of violation behavior, and the third type of violation behavior, respectively, and combine with the coal mine production and the equipment aging label to construct index constraints, retrieve the first type of coal mine production sample set, the second type of coal mine production sample set, and the third type of coal mine production sample set, respectively, calculate the accident sample proportion, and obtain the first type of coal mine production accident trigger probability, the second type of coal mine production accident trigger probability, and the third type of coal mine production accident trigger probability.

[0101] In the embodiments of the present application, in order to ensure that the accident risk under different combinations of violation behaviors, production loads, and equipment states can be reflected in different levels, it is necessary to construct index constraints and retrieve sample sets to divide the three types of production scheduling sample sets and calculate the accident trigger probability, which provides decision basis for the final production scheduling scheme optimization.

[0102] Specifically, first, a type of violation behavior is traversed, and a first coal mine production scheduling sample set that matches the constraint conditions is retrieved from the historical coal mine production scheduling records under the double constraints of the specific performance of the type of violation behavior and the randomly configured coal mine production.

[0103] Further, the sample equipment state account of the first coal mine production scheduling sample is extracted from the first coal mine production scheduling sample set, and the sample equipment aging label is calibrated in the same process as the calibration of the current equipment aging label.

[0104] When the sample equipment aging label is consistent with the currently generated equipment aging label, the first coal mine production scheduling sample is included in the coal mine production scheduling sample set.

[0105] Further, the second type of violation behavior and the third type of violation behavior are processed by the same process. That is, for the second type of violation behavior, a second coal mine production scheduling sample set is retrieved under the constraint of the coal mine production, and a second coal mine production scheduling sample set is constructed through the matching of the sample equipment aging label and the current equipment aging label; for the third type of violation behavior, a third coal mine production scheduling sample set is constructed in the same way.

[0106] Finally, the proportions of samples that have occurred production accidents in the three coal mine production scheduling sample sets are calculated, respectively, and are sequentially used as the first coal mine production accident triggering probability, the second coal mine production accident triggering probability, and the third coal mine production accident triggering probability.

[0107] This step realizes the accurate retrieval and accident probability quantification of historical samples in the same risk scenario by associating the personnel violation behavior, the coal mine production, and the equipment state to construct index constraints, and provides a multi-dimensional probability basis for subsequent production scheduling strategies based on risk levels.

[0108] The step S140 in the method provided in the embodiments of the present application includes:

[0109] A first violation behavior is extracted from the type of violation behavior;

[0110] A first coal mine production scheduling sample set is retrieved under the constraint of the first violation behavior and the coal mine production;

[0111] A sample equipment state account of the first coal mine production scheduling sample in the first coal mine production scheduling sample set is extracted, and a sample equipment aging label is calibrated;

[0112] When the sample equipment aging label is the same as the equipment aging label, the first coal mine production scheduling sample is added to the first coal mine production scheduling sample set;

[0113] The determination processes of the second coal mine production scheduling sample set and the third coal mine production scheduling sample set are the same as those of the first coal mine production scheduling sample set.

[0114] In the embodiments of the present application, in order to ensure that the accident risks under different violation behaviors, production loads and equipment state combinations can be reflected in different levels, three types of production scheduling sample sets are constructed through hierarchical search and sample matching, thereby providing a standardized sample basis for subsequent accident triggering probability calculation.

[0115] Specifically, first, a specific first violation behavior is extracted from a type of violation behavior. For example, a specific violation action with a safety event triggering probability greater than a threshold value.

[0116] For example, if a coal mining machine driver does not check the hydraulic system pressure to the rated value before starting the machine (the safety event triggering probability is 15%, and the threshold value is 10%), the action is taken as the first violation behavior.

[0117] Further, all samples that meet the constraint in the historical coal mine production scheduling records are searched under the double constraint conditions of the first violation behavior and the randomly configured coal mine production, and a first-level coal mine production scheduling sample set is formed.

[0118] For example, if the first violation behavior is that the coal mining machine driver does not check the hydraulic system pressure to the rated value before starting the machine, and the randomly configured coal mine production is 5000 tons / day, all samples of the historical production scheduling records in which the coal mining machine driver has the behavior of not checking the hydraulic system pressure to the rated value before starting the machine and the daily production is 5000 tons / day are searched, and these samples are aggregated to form a first-level coal mine production scheduling sample set.

[0119] Further, a first coal mine production scheduling sample is selected from the obtained first-level coal mine production scheduling sample set, and a sample equipment state account corresponding to the first coal mine production scheduling sample is extracted. The sample equipment aging label of the sample is labeled according to a process completely consistent with the current device aging label, that is, the stable probability is generated and integrated through the operation stable probability prediction channel special for each device type, and the sample equipment aging label of the sample is labeled.

[0120] If the sample equipment aging label is completely consistent with the current generated device aging label, the first coal mine production scheduling sample is included in the first coal mine production scheduling sample set.

[0121] For example, a first coal mine production scheduling sample is selected from the above-mentioned first-level coal mine production scheduling sample set, and the sample equipment state account of the first coal mine production scheduling sample includes the state parameters of the first number of roadheader (service time 7500 hours, maintenance frequency every month 3 times), the Q number of ventilator (service time 11000 hours, maintenance frequency every month 5 times) and other equipment.

[0122] Meanwhile, according to the equipment aging label calibration process, a stable probability (72% for the tunneling machine, 48% for the ventilator, etc.) is generated through a respective dedicated prediction channel, and is integrated into a sample equipment aging label. If the sample equipment aging label is completely consistent with the current equipment aging label (72% for the tunneling machine, 48% for the ventilator, etc.), the sample is added to a type I coal mine production scheduling sample set.

[0123] Similarly, for type II and type III violations, the same processing flow as type I violations is used to construct type II and type III coal mine production scheduling sample sets, respectively.

[0124] Finally, type II coal mine production scheduling sample sets (such as containing type II violation samples such as "gas detector not carrying gas detector as required") and type III coal mine production scheduling sample sets (such as containing type III violation samples such as "transport worker not walking on standard route during operation") are constructed through the same logic, which together form a production scheduling sample system covering all risk levels.

[0125] This process realizes accurate screening of historical production scheduling samples in the same risk scenario by taking personnel violation behavior, coal mine production, and equipment state as correlation constraints, ensures that the three sample sets correspond to different violation risk levels and equipment, production state combination scenarios, provides a standardized and comparable sample basis for subsequent calculation of production accident trigger probabilities in each category, and makes the final probability calculation result truly reflect the likelihood of accidents in different risk scenarios.

[0126] On this basis, the method provided by the embodiment of the application further includes:

[0127] When any one of the type I coal mine production accident trigger probability, the type II coal mine production accident trigger probability, and the type III coal mine production accident trigger probability is greater than the accident trigger probability threshold, it is determined whether the coal mine production is less than the production threshold;

[0128] If greater than or equal to, based on a preset gradient, the coal mine production is reduced to obtain an updated coal mine production execution cycle;

[0129] If less than, a production risk prompt is given to the coal mine production line at the user end.

[0130] In the embodiment of the application, after the corresponding accident trigger probability is calculated through the type III coal mine production scheduling sample set, in order to realize dynamic prevention and control of production risk and optimization balance of production capacity, the coal mine production capacity needs to be closed-loop controlled through threshold judgment and stepwise adjustment to ensure production continuity under controllable risk.

[0131] Specifically, first, the calculated first type of coal mine production accident triggering probability, the second type of coal mine production accident triggering probability and the third type of coal mine production accident triggering probability are compared with the preset accident triggering probability threshold value respectively.

[0132] When any type of coal mine production accident triggering probability value exceeds the threshold value, it indicates that the current production combination (corresponding to the irregular behavior, equipment state and production capacity) has a high safety risk, and the production capacity adjustment process needs to be started immediately.

[0133] For example, if the preset accident triggering probability threshold value is 10%, the calculated first type of coal mine production accident triggering probability is 15%, the second type is 8%, and the third type is 5%, since the first type of probability exceeds the threshold value, it indicates that the current production combination has a high safety risk, and the production capacity adjustment process needs to be started immediately.

[0134] Further, after starting the production capacity adjustment process, it is judged whether the current coal mine production capacity is less than the production capacity threshold value. The production capacity threshold value is set based on the coal mine capacity design and safety regulations, for example, the production capacity threshold value of a certain coal mine is 4000 tons / day.

[0135] Specifically, if the current production capacity is greater than or equal to the production capacity threshold value, it indicates that there is a space to avoid risks by reducing production capacity, at this time, the production capacity is reduced based on the preset gradient, the updated coal mine production capacity is generated, and the whole process is re-executed, that is, the equipment aging label is recalibrated, the personnel behavior is classified, the production capacity is configured, and the accident triggering probability is calculated, until all types of accident triggering probabilities are below the threshold value or the production capacity has been reduced to below the threshold value.

[0136] For example, if the calculated first type of coal mine production accident triggering probability is 18% (the accident triggering probability threshold value is 10%), the current coal mine production capacity is 5000 tons / day (the production capacity threshold value is 4000 tons / day), and since the production capacity is greater than the threshold value, the production capacity is reduced by 500 tons / day each time according to the preset gradient to 4500 tons / day and the cycle is re-executed; if the recalculated second type of coal mine production accident triggering probability is still 12% (>10%), the production capacity is continued to be reduced to 4000 tons / day to execute the cycle again until the condition is met.

[0137] On the contrary, if the current production capacity is less than the production capacity threshold value, it indicates that there is no space for reduction, and continuing production may face uncontrollable risks, at this time, a production risk prompt needs to be issued on the user end for targeted measures.

[0138] The method provided in the embodiment of the present application comprises the following steps:

[0139] The first bit number device stability probability of the device aging label is set to 0 to obtain an updated device aging label.

[0140] Traversing the first, second, and third types of violations, respectively, combining them with the production volume threshold and the update equipment aging tag to construct index constraints, and calculating the probability of triggering a first, second, and third type of updated coal mine production accidents;

[0141] When the trigger probability of the first type of updated coal mine production accident, the trigger probability of the second type of updated coal mine production accident, and the trigger probability of the third type of updated coal mine production accident are all less than or equal to the accident trigger probability threshold, the first number device is added to the risk warning device;

[0142] Until the analysis of all the position numbered devices is completed, the risk warning device will issue a production risk warning to the coal mine production line at the user end according to the risk warning device.

[0143] In the embodiment of the present application, in a scenario where the coal mine production is less than the production threshold and the probability of accident triggering still exceeds the standard, in order to accurately locate the source of the risk and generate targeted production risk warnings, it is necessary to accurately identify the risk equipment through individual and associated analysis of the equipment risks one by one to ensure that the prompt content focuses on key hidden dangers.

[0144] Specifically, first, for the first device number included in the device aging label, its stability probability is forcibly set to 0 (to simulate the extreme risk state of complete failure of the device), and an updated device aging label is generated.

[0145] For example, if the first-numbered device is a coal mine roadheader, its stability probability in the device aging label is 72%. After it is forcibly set to 0, the stability probability of the device in the updated device aging label becomes 0, and the remaining numbered devices (such as the Q-numbered ventilator 48%) remain unchanged.

[0146] Among them, this step can intuitively assess the impact of a single device on the overall production risk by isolating the risk of the device.

[0147] Furthermore, we traverse the first, second and third category violations, and use the various types of violations, the current production volume threshold and the updated equipment aging label as triple constraints to rebuild the index constraint, retrieve the corresponding updated coal mine production scheduling sample set, and count the proportion of accident samples therein to obtain the first, second and third category updated coal mine production accident triggering probabilities.

[0148] Among them, because the coal mine production is less than the production threshold, the production threshold is fixed as the production load parameter at this time.

[0149] Exemplarily, if the production threshold is 4000 tons / day, and the current coal mine production is 3500 tons / day (less than the threshold), the production load parameter is uniformly set as 4000 tons / day at the time of retrieval, combined with the first type of violation behavior of "coal mining machine driver not checking hydraulic system pressure" and updating the equipment aging label (drilling machine stability probability 0%), the sample set matching the constraints in the history is retrieved.

[0150] Further, when the updated coal mine production accident trigger probability is less than or equal to the accident trigger probability threshold, it indicates that the first serial number equipment is the key factor causing the original risk to exceed the standard, and it is added to the risk prompt equipment list. If the probability still exceeds the standard after updating, it means that the equipment is not the core risk source and is not included in the prompt list.

[0151] Exemplarily, if the accident trigger probability threshold is 10%, and the original first type of coal mine production accident trigger probability is 15% (exceeding the standard), the first serial number drilling machine stability probability is set to 0, and the calculated first type of updated probability is 8% (≤10%), it is determined that the drilling machine is a key risk source and is added to the risk prompt equipment list.

[0152] Similarly, the second serial number to the Q serial number equipment are analyzed in turn according to the above processing procedure, that is, the stability probability of each serial number equipment is set to 0 to generate the corresponding updated equipment aging label, and the constraint construction and accident trigger probability calculation steps are repeated until the risk test of all serial number equipment is completed.

[0153] Exemplarily, when analyzing the second serial number scraper conveyor (original stability probability 85%), the stability probability is set to 0 to generate a new updated equipment aging label, combined with the second type of violation behavior "not carrying gas detector as required" and the production threshold 4000 tons / day, the second type of updated probability is calculated as 12% (still exceeding the standard), it is determined that the scraper conveyor is not a core risk source and is not included in the list.

[0154] Finally, the production risk prompt is generated at the user end according to the risk prompt equipment list, which contains the equipment serial number that needs to be focused on, its current stability probability and the associated risk scene, providing clear targets for on-site personnel to investigate and intervene.

[0155] Exemplarily, the risk prompt content can be "risk prompt equipment: first serial number drilling machine (current stability probability 72%), this equipment combined with the violation behavior of "not checking hydraulic system pressure" and 4000 tons / day production is the key factor causing the accident trigger probability to exceed the standard, please prioritize maintenance".

[0156] The process realizes the dynamic balance of production capacity and safety risk through the closed-loop scheme of "threshold judgment-gradient adjustment-cycle verification-risk prompt", avoids the efficiency loss caused by blind shutdown, prevents risk accumulation through timely intervention, and provides a flexible and rigorous management and control mechanism for coal mine safety production.

[0157] S150: When the trigger probability of a type of coal mine production accident, the trigger probability of a type of coal mine production accident, and the trigger probability of a type of coal mine production accident are all less than or equal to the accident trigger probability threshold, production management is performed according to the coal mine production capacity.

[0158] In the embodiments of the present application, in the scenario where the trigger probabilities of the three types of coal mine production accidents are all within the safe and controllable range, in order to realize the collaborative optimization of production efficiency and stable operation of equipment, the current coal mine production capacity is taken as the benchmark, and the production line is managed by combining the equipment state and personnel behavior specification, so as to ensure accurate matching of operation parameters and production demand at each link.

[0159] Specifically, first, taking the risk-verified coal mine production capacity as the core parameter, for the first number equipment of the coal mine production line, according to its stability probability in the equipment aging label, the operation parameters adapted to the current production capacity are generated by calling the work stability probability prediction channel bound to the equipment model, so as to ensure that the equipment load and the production target are matched.

[0160] For example, if the first number equipment is a heading machine, its stability probability in the equipment aging label is 72%, and the current coal mine production capacity is 5000 tons / day. Through the work stability probability prediction channel bound to the heading machine model, the operation parameters "work power 80%, start-stop interval every 5 minutes" are generated, so that the heading efficiency is adapted to the production demand of 5000 tons / day.

[0161] Similarly, the same operation is performed on the second number to the Qth number equipment of the coal mine production line, that is, according to the stability probability and model characteristics of each equipment, the operation parameters adapted to the current production capacity are generated through the corresponding work stability probability prediction channel, so that the dynamic balance between the operation state of the whole production line equipment and the production demand is formed.

[0162] For example, the second number equipment is a scraper conveyor, and the stability probability is 85%. Combined with the production capacity of 5000 tons / day, the operation parameters "conveying speed 1.2 m / s, clean coal every 30 minutes" are generated through the exclusive work stability probability prediction channel of the scraper conveyor; the Qth number equipment is a ventilator, and the stability probability is 48%. Correspondingly, the parameters "air volume 3000 m 3 / h, air pressure 2500 Pa" are generated, so as to ensure that the ventilation efficiency matches the current production scale.

[0163] Meanwhile, combined with the classification results of the first, second and third types of irregular behaviors, the corresponding post personnel are pushed the operation specification guidance matching the current production capacity, such as for the post where the first type of irregular behavior has occurred, the execution standard prompt of the key steps is strengthened to ensure that the personnel behavior is consistent with the equipment operation and production capacity target.

[0164] For example, if the first type of irregular behavior includes "coal mining machine driver does not check hydraulic system pressure", and the current production capacity is 5000 tons / day, the coal mining machine driver is pushed the operation guidance of "check the hydraulic system pressure every hour to ensure that the pressure is maintained in the range of 15-20 MPa"; for the second type of irregular behavior "not carrying gas detector as required", the gas detector is pushed the specification prompt of "recording gas concentration every 2 hours and uploading detection data synchronously".

[0165] Finally, the equipment operation parameters and personnel operation specifications are integrated into a unified production scheduling management scheme to realize the systematic linkage from equipment operation to personnel operation of the whole production line.

[0166] This step constructs a "production capacity-equipment-personnel" management system by adapting production parameters to each equipment by number and linking personnel behavior specifications, which plays the maximum production efficiency under the current production capacity on the premise of ensuring operation safety, and provides accurate management basis for the efficient and stable operation of the coal mine production line.

[0167] Through the specific implementation manner described above, the embodiment of the present application achieves the following technical effects:

[0168] The coal mine safety production analysis method fusing multi-modal data is proposed, first, based on the equipment state account, the service time and maintenance frequency of each equipment are extracted, the stable probability is generated through the operation stable probability prediction channel bound to the equipment model, and integrated into the equipment aging label; the personnel behavior data is classified to determine the first, second and third types of irregular behaviors, and the coal mine production capacity is randomly configured; then, combined with the three, the index constraint is constructed, the first, second and third coal mine production scheduling sample sets are retrieved, and the first, second and third coal mine production accident trigger probabilities are calculated; finally, according to whether the probability meets the standard, the production scheduling management is executed, or the production capacity is adjusted according to the preset gradient, the risk is prompted on the user side and the risk equipment is accurately positioned, forming a whole-process closed-loop management. This process realizes the collaborative management of multi-dimensional data such as production efficiency, equipment state and personnel behavior, and provides a complete solution for the balance between operation safety and production efficiency.

[0169] The method provided in the embodiment of the present application realizes the fusion and integrated management of multimodal data through the technical solution of "equipment aging label calibration - personnel violation classification - coal mine production volume configuration - accident trigger probability calculation - production scheduling management", and solves the technical problems existing in traditional coal mine production scheduling management, such as insufficient coordination between equipment status, personnel behavior and output demand, resulting in high safety risks and low production efficiency. It provides an accurate and efficient management solution for coal mine production scheduling, which not only ensures maximization of production efficiency under the premise of controllable risks, but also effectively improves the comprehensiveness of mining production management by coordinating multi-dimensional factors.

[0170] Example 2, as shown in the attached Figure 2 As shown, based on the inventive concept of the coal mine production safety analysis method for fusing multimodal data provided in Example 1, this application also provides a coal mine production safety analysis system for fusing multimodal data, specifically including:

[0171] Equipment aging calibration module 01 is used to calibrate equipment aging labels based on pre-stored equipment status records;

[0172] Personnel Violation Classification Module 02 is used to classify the behavior data of personnel whose service time is less than or equal to the service time threshold, and determine Class I, Class II, and Class III violations. Class I violations represent violations whose security event triggering probability is greater than or equal to the triggering probability threshold, Class II violations represent violations whose security event triggering probability is less than the triggering probability threshold and greater than 0, and Class III violations represent violations that are inconsistent with standard behavior and whose security event triggering probability is equal to 0;

[0173] Randomly configure production module 03, used to randomly configure coal mine production;

[0174] The accident probability calculation module 04 is used to traverse the first type of violation, the second type of violation, and the third type of violation, respectively, and combine them with the coal mine production volume and the equipment aging label to construct an index constraint, retrieve the first type of coal mine production scheduling sample set, the second type of coal mine production scheduling sample set, and the third type of coal mine production scheduling sample set, respectively calculate the accident sample ratio, and obtain the first type of coal mine production accident triggering probability, the second type of coal mine production accident triggering probability, and the third type of coal mine production accident triggering probability;

[0175] The production scheduling management module 05 is used to perform production scheduling management according to the coal mine production volume when the probability of triggering a Class I coal mine production accident, the probability of triggering a Class II coal mine production accident, and the probability of triggering a Class III coal mine production accident are all less than or equal to the accident trigger probability threshold.

[0176] In one embodiment, the device aging calibration module 01 is further configured to:

[0177] From the device state account, the service length and maintenance frequency of the first number device of the coal mine production line are extracted, and the first number device stability probability is generated through the first operation stability probability prediction channel processing bound to the first number device model, wherein the device stability probability represents the probability of device operation accident.

[0178] Until the Qth number device service length and the Qth number device maintenance frequency of the coal mine production line are extracted from the device state account, the Qth number device stability probability is generated through the Qth operation stability probability prediction channel processing bound to the Qth number device model.

[0179] The first number device stability probability to the Qth number device stability probability is added to the device aging label.

[0180] In one embodiment, the personnel violation classification module 02 is also used for:

[0181] From the personnel behavior data, the first personnel behavior data is extracted, wherein the first personnel behavior data includes the execution post number and the execution action.

[0182] Based on the execution post number, the pre-constructed standard action library is inputted, and the standard behavior is matched, wherein the standard behavior includes the standard execution action.

[0183] When the execution action and the standard execution action are inconsistent, the execution post number historical operation record is retrieved with the execution action as a constraint.

[0184] The safety accident triggering transaction proportion in the execution post number historical operation record is counted and set as the safety event triggering probability.

[0185] Based on the trigger probability threshold value set by the user end in advance, the first personnel behavior data is classified in combination with the safety event triggering probability.

[0186] When all personnel behavior data analysis is completed, the first type of violation behavior, the second type of violation behavior and the third type of violation behavior are outputted.

[0187] In one embodiment, the accident probability calculation module 04 is also used for:

[0188] From the first type of violation behavior, the first violation behavior is extracted.

[0189] With the first violation behavior and the coal mine production as constraints, the first level coal mine production sample set is retrieved.

[0190] The sample device state account of the first coal mine production sample of the first level coal mine production sample set is extracted, and the sample device aging label is calibrated.

[0191] when the sample device aging label is same as the device aging label, adding the first coal mine production sample into the first coal mine production sample set;

[0192] wherein, the determination process of the second coal mine production sample set and the third coal mine production sample set is same as the first coal mine production sample set.

[0193] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of the present application are described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0194] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0195] The present application and the drawings are only exemplary description of the present application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A coal mine safety production analysis method integrating multimodal data, characterized in that: include: Based on the pre-stored equipment status ledger, calibrate the equipment aging label; Classify the behavioral data of personnel whose service time is less than or equal to the service time threshold to determine Class I, Class II, and Class III violations. Class I violations represent violations with a security incident triggering probability greater than or equal to the triggering probability threshold; Class II violations represent violations with a security incident triggering probability less than the triggering probability threshold and greater than 0; Class III violations represent violations that are inconsistent with standard behavior and have a security incident triggering probability equal to 0; Randomly allocate coal mine production; Traverse the first, second, and third types of violations, respectively combine them with the coal mine production volume and the equipment aging label to build index constraints, retrieve the first, second, and third types of coal mine production scheduling sample sets, calculate the accident sample ratios, and obtain the first, second, and third types of coal mine production accident triggering probabilities; When the probability of triggering a Class I coal mine production accident, the probability of triggering a Class II coal mine production accident, and the probability of triggering a Class III coal mine production accident are all less than or equal to the accident trigger probability threshold, production scheduling management is performed based on the coal mine production volume.

2. The method according to claim 1, wherein Based on the pre-stored equipment status ledger, calibrate the equipment aging label, including: Extract the service time and maintenance frequency of the first equipment in the coal mine production line from the equipment status ledger, and process them through the first operation stability probability prediction channel bound to the first equipment model to generate the stability probability of the first equipment. The equipment stability probability represents the probability of an accident occurring during the equipment operation. Until the service life and maintenance frequency of the Q-th equipment in the coal mine production line are extracted from the equipment status ledger, and the stability probability of the Q-th equipment is generated by processing the Q-th operation stability probability prediction channel bound to the Q-th equipment model; The stability probabilities of the first-numbered devices up to the Q-th-numbered devices are added to the device aging tag.

3. The method according to claim 2, wherein The service life and maintenance frequency of the first equipment in the coal mine production line are extracted from the equipment status ledger. The stability probability of the first equipment is generated by processing the first operation stability probability prediction channel bound to the model of the first equipment, including: Retrieve multiple pieces of first-number device model operation record data, wherein any piece of the plurality of first-number device model operation record data includes first-number device service time record data, first-number device maintenance frequency record data, and a device fault trigger flag, where when the flag is equal to 1, it is considered that the device fault state is triggered, and when the flag is equal to 0, it is considered that the device healthy operation state is triggered; Traversing the plurality of first-numbered device model operation record data, and retrieving a plurality of supplementary device fault trigger identifiers of the first-numbered device model based on the first-numbered device service time record data and the first-numbered device maintenance frequency record data as constraints; Counting the proportion of 0 values ​​in the plurality of supplementary device fault trigger identifiers and the device fault trigger identifiers, and setting the result as a label identifying the stability probability of the first-numbered device; Using the label of the stability probability of the first-numbered device as supervision, and the service time record data and maintenance frequency record data of the first-numbered device as input, the multiple operation record data of the first-numbered device model are retrieved, and through machine learning, the first operation stability probability prediction channel is trained and bound to the first-numbered device model.

4. The method according to claim 1, wherein The behavioral data of personnel whose service time is less than or equal to the service time threshold is classified into Category 1, Category 2, and Category 3 violations, including: Extracting first personnel behavior data from the personnel behavior data, wherein the first personnel behavior data includes an execution position number and an execution action; Based on the execution position number, a pre-built standard action library is input to match standard behaviors, wherein the standard behaviors include standard execution actions; When the execution action is inconsistent with the standard execution action, the historical operation records of the execution position number are retrieved based on the execution action as a constraint; Counting the proportion of security incident triggering transactions in the historical job records of the execution post number, and setting it as the security incident triggering probability; Classifying the first personnel behavior data based on the trigger probability threshold preset by the user terminal and the security event trigger probability; When the analysis of all personnel behavior data is completed, the first type of violation, the second type of violation, and the third type of violation are output.

5. The method according to claim 1, wherein Traverse the first, second, and third types of violations, respectively combine them with the coal mine production volume and the equipment aging label to build index constraints, retrieve the first, second, and third types of coal mine production scheduling sample sets, calculate the accident sample ratios, and obtain the first, second, and third types of coal mine production accident triggering probabilities, including: Extracting a first violation from the class of violations; Retrieving a first-level coal mine production scheduling sample set based on the first violation and the coal mine production volume as constraints; Extracting the sample equipment status ledger of the first coal mine production scheduling sample of the first-level coal mine production scheduling sample set, and calibrating the aging label of the sample equipment; When the sample equipment aging label is the same as the equipment aging label, adding the first coal mine production scheduling sample to the first type of coal mine production scheduling sample set; Among them, the determination process of the second-category coal mine production scheduling sample set and the third-category coal mine production scheduling sample set is the same as that of the first-category coal mine production scheduling sample set.

6. The method according to claim 2, wherein Also includes: When any one of the probability of triggering a Class I coal mine production accident, the probability of triggering a Class II coal mine production accident, and the probability of triggering a Class III coal mine production accident is greater than the accident trigger probability threshold, determining whether the coal mine production volume is less than the production volume threshold; If it is greater than or equal to, based on a preset gradient, the coal mine production is reduced to obtain an updated coal mine production execution cycle; If it is less than that, a production risk warning will be issued to the coal mine production line at the user end.

7. The method according to claim 6, wherein If it is less than that, the user will be prompted with production risk warnings for the coal mine production line, including: Setting the device stability probability of the first bit number of the device aging tag to 0, and obtaining an updated device aging tag; Traversing the first, second, and third types of violations, respectively, combining them with the production volume threshold and the update equipment aging tag to construct index constraints, and calculating the probability of triggering a first, second, and third type of updated coal mine production accidents; When the trigger probability of the first type of updated coal mine production accident, the trigger probability of the second type of updated coal mine production accident, and the trigger probability of the third type of updated coal mine production accident are all less than or equal to the accident trigger probability threshold, the first number device is added to the risk warning device; Until the analysis of all the position numbered devices is completed, the risk warning device will issue a production risk warning to the coal mine production line at the user end according to the risk warning device.

8. A coal mine safety production analysis system integrating multimodal data is characterized by: The system is used to execute the coal mine production safety analysis method for fusing multimodal data according to any one of claims 1 to 7, and the system includes: Equipment aging calibration module, used to calibrate equipment aging labels based on pre-stored equipment status records; A personnel violation classification module is used to classify the behavioral data of personnel whose service time is less than or equal to the service time threshold, and determine Class I, Class II, and Class III violations. Class I violations represent violation types with a security event triggering probability greater than or equal to the triggering probability threshold, Class II violations represent violation types with a security event triggering probability less than the triggering probability threshold and greater than 0, and Class III violations represent violations that are inconsistent with standard behavior and have a security event triggering probability equal to 0; Randomly configure the output module, used to randomly configure the coal mine production; An accident probability calculation module is used to traverse the first type of violation, the second type of violation, and the third type of violation, respectively combine them with the coal mine production volume and the equipment aging label to construct index constraints, retrieve the first type of coal mine production scheduling sample set, the second type of coal mine production scheduling sample set, and the third type of coal mine production scheduling sample set, respectively calculate the accident sample ratio, and obtain the first type of coal mine production accident triggering probability, the second type of coal mine production accident triggering probability, and the third type of coal mine production accident triggering probability; The production scheduling management module is used to perform production scheduling management according to the coal mine production volume when the probability of triggering a Class I coal mine production accident, the probability of triggering a Class II coal mine production accident, and the probability of triggering a Class III coal mine production accident are all less than or equal to the accident trigger probability threshold.

Images