A dust prediction and air curtain partitioning regulation method for a tunneling working face

Abstract

The present disclosure relates to the technical field of coal mine underground ventilation dust control, and particularly relates to a tunneling working face dust prediction and air curtain partition regulation and control method. The method comprises: using a prediction model to identify the space-time characteristic data of the multi-source state data of the tunneling working face in a continuous time window, and obtaining a state prediction result; under the condition that the set of operation conditions of the tunneling working face meets the ventilation safety constraint and the equipment operation constraint, according to the corresponding control target of the tunneling working face, the MPC module processes the multi-source state data, the state prediction result and the cutting position data, and obtains the control sequence of multiple control compensations in the prediction length and the target control quantity corresponding to each air curtain action area in the current control period; according to the deviation between the target control quantity and the feedback quantity and the control sequence, the target actuator is subjected to closed-loop compensation control. The accuracy of coal mine underground ventilation and dust control is improved.

Description

Technical Field

[0001] This disclosure relates to the field of ventilation and dust control technology in coal mines, and in particular to a method for predicting dust and controlling air curtain zones in tunneling working faces. Background Technology

[0002] Coal mine tunneling faces generate a large amount of dust during the cutting process, accompanied by the release of harmful gases such as methane. Due to the narrow space and dense equipment layout in the tunneling roadways, and the constantly changing cutting positions, dust and methane easily accumulate locally at the face, tunneling work area, and return air side, adversely affecting the health of workers and mine safety. Some air curtain control methods in various embodiments rely on real-time monitoring results such as dust concentration, wind speed, or methane concentration for feedback adjustment, making it difficult to utilize pre-existing dust source information such as the cutting mechanism's position and cutting direction. Furthermore, the dust migration, blocking, dilution, and extraction processes are also affected by ventilation facility operating parameters such as main airflow velocity, air curtain volume, guide angle, short-range negative pressure, and extraction volume. Adjusting solely based on a single dust concentration or cutting position fails to reflect the differences in dust source impact and ventilation engineering effects across different air curtain action areas, easily leading to problems such as insufficient local air curtain strength, mismatched guide angles, or unreasonable airflow distribution. Therefore, how to effectively isolate, guide, and extract dust at the face of the mine while ensuring effective air supply and gas dilution, and simultaneously considering dust source factors and ventilation effects, is a problem that needs to be solved in the field of underground ventilation and dust control in coal mines. Summary of the Invention

[0003] This disclosure provides a method for dust prediction and air curtain zoning control in tunneling working faces. It simultaneously considers dust source factors and ventilation engineering factors, predicts and optimizes the target airflow and guide angle for different air curtain action areas, and improves the accuracy of air curtain control through closed-loop compensation control, thereby enhancing the accuracy of ventilation and dust control in coal mines. The technical solution of this disclosure is as follows: According to a first aspect of the present disclosure, a method for dust prediction and air curtain zoning control at a tunneling working face is provided, comprising: Collect multi-source status data of the tunneling face within a continuous time window, wherein the multi-source status data includes the working data of the tunneling face, cutting position data, ventilation facility operation parameters, and regional data of each air curtain action area; Obtain the spatiotemporal feature data corresponding to the multi-source state data; A prediction model is used to identify the spatiotemporal feature data and obtain state prediction results, which include the predicted dust concentration and / or predicted wind speed in each wind curtain area. Under the condition that the set of operating conditions of the tunneling face satisfies the ventilation safety constraints and equipment operation constraints, according to the control target corresponding to the tunneling face, the MPC module is controlled to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operation parameters to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure. Based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence, closed-loop compensation control is performed on the target actuator, wherein the target actuator includes at least one of the following: an inlet fan, an outlet fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator.

[0004] According to some embodiments, the step of performing closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity includes: A PID model is used to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity.

[0005] According to some embodiments, the prediction model includes at least one of a CNN-LSTM model, an LSTM model, a GRU model, or a Transformer temporal model. The step of using the prediction model to identify the spatiotemporal feature data and obtain state prediction results includes: Extract the spatial distribution characteristics between each detection location in the tunneling face; Extract the variation characteristics of the multi-source state data within a continuous time window, and obtain the state prediction result based on the spatial distribution characteristics and the variation characteristics.

[0006] According to some embodiments, the method further includes: Based on the predicted dust concentration in each air curtain's effective area, the total target air volume of the air curtain, the weight of each air curtain's effective area, the dust generation position correction factor of the cutting mechanism relative to each air curtain's effective area, and the ventilation effect correction factor, the target air volume corresponding to each air curtain's effective area is obtained.

[0007] According to some embodiments, the method further includes: Based on the predicted dust concentration in each air curtain operating area, the wind speed in each air curtain operating area, the dust generation position correction factor of the cutting mechanism relative to each air curtain operating area, and the ventilation effect correction factor, the guiding target angle corresponding to each air curtain operating area is obtained.

[0008] According to some embodiments, the method further includes: The dust generation location correction factor is determined based on the current position of the cutting mechanism, the cutting direction, the position change of the cutting mechanism within a continuous time window, and the spatial coverage of each wind curtain's effective area. Specifically, when the current position of the cutting mechanism is within the spatial coverage of the target wind curtain's effective area, or when it is determined based on the position change of the cutting mechanism within a continuous time window that it will enter the spatial coverage of the target wind curtain's effective area in the subsequent prediction time domain, the dust generation location correction factor corresponding to the target wind curtain's effective area is increased.

[0009] According to some embodiments, the ventilation effect correction factor is determined based on at least one of the following: main airflow velocity, actual wind speed in each air curtain area, air curtain volume, guide angle, short exhaust negative pressure, exhaust volume, and relative position between the air curtain area and the short exhaust inlet. It is used to characterize the influence of ventilation facility operating parameters on the dust migration, blocking, dilution, or exhaust effect in each air curtain area.

[0010] According to some embodiments, the method further includes: Based on the set of status evaluation parameters and the weights corresponding to each status evaluation parameter in the set of status evaluation parameters, the status evaluation of the air curtain effect corresponding to the tunneling face is obtained, and the target air volume and / or target guide angle for the next control cycle are corrected based on the status evaluation of the air curtain effect. The set of status evaluation parameters includes at least one of the following: dust concentration behind the air curtain, dust concentration on the return air side, short-run negative pressure deviation, and zoned air curtain wind speed deviation.

[0011] According to a second aspect of the present disclosure, a dust prediction and air curtain zoning control device for tunneling working faces is provided, comprising: The data acquisition unit is used to acquire multi-source status data of the tunneling face within a continuous time window. The multi-source status data includes the working data of the tunneling face, the cutting position data, the operating parameters of the ventilation facilities, and the regional data of each air curtain's effective area. The data acquisition unit is also used to acquire spatiotemporal feature data corresponding to the multi-source state data; The result acquisition unit is used to identify the spatiotemporal feature data using a prediction model and obtain the state prediction result. The control quantity acquisition unit is used to control the MPC module to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operation parameters according to the control target corresponding to the tunneling face, under the condition that the set of operating conditions of the tunneling face meets the ventilation safety constraints and equipment operation constraints, and to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure. The mechanism control unit is used to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence, wherein the target actuator includes at least one of the following: an inlet fan, an outlet fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator.

[0012] According to a third aspect of the present disclosure, an electronic device is provided, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the method for dust prediction and air curtain zoning control at the tunneling working face, as described in any of the preceding aspects.

[0013] According to a fourth aspect of the present disclosure, a storage medium is provided that, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform a method for predicting dust and controlling air curtain zones at a tunneling working face, as described in any of the preceding aspects.

[0014] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described in any one of the preceding aspects.

[0015] The technical solutions provided by the embodiments of this disclosure have at least the following beneficial effects: In some or related embodiments, multi-source state data of the tunneling face within a continuous time window is collected. This multi-source state data includes working data, cutting position data, ventilation facility operating parameters, and regional data of each air curtain's effective area. Spatiotemporal feature data corresponding to the multi-source state data is obtained. A prediction model is used to identify the spatiotemporal feature data to obtain state prediction results. Under the condition that the set of operating conditions of the tunneling face satisfies ventilation safety constraints and equipment operating constraints, the control MPC module performs rolling optimization processing on the multi-source state data, state prediction results, cutting position data, and ventilation facility operating parameters to obtain multiple candidate control sequences in the prediction time domain and target control quantities corresponding to each air curtain's effective area in the current control cycle. Closed-loop compensation control is then performed based on the deviation between the target control quantity and the feedback quantity and the candidate control sequences. Therefore, this disclosure can utilize dust source pre-information such as cutting position and cutting direction, and combine it with ventilation facility operating parameters such as main airflow velocity, air curtain volume, guide angle, short-range negative pressure and exhaust volume, to differentiate and regulate the effective areas of each air curtain, reduce the lag of simple threshold feedback control, and improve the accuracy of air curtain regulation and the accuracy of ventilation and dust control in coal mines.

[0016] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0018] Figure 1 This is a flowchart of the first method for dust prediction and air curtain zoning control at the tunneling working face provided in this embodiment of the present disclosure; Figure 2 This is a flowchart of the second method for dust prediction and air curtain zoning control at the tunneling working face provided in this embodiment of the present disclosure; Figure 3 The diagram shown is an example schematic of a dust prediction and air curtain zoning control system for tunneling workfaces provided in an embodiment of this disclosure. Figure 4 The diagram shown is an example schematic diagram of a dust prediction and air curtain zoning control device for a tunneling working face provided in an embodiment of this disclosure; Figure 5 The diagram shown is an example of a method for predicting dust and controlling air curtain zones at a tunneling working face, provided by an embodiment of this disclosure. Figure 6 The diagram shown is an example schematic of an MPC rolling optimization control method provided in an embodiment of this disclosure; Figure 7 The diagram shown is an example of a method for calculating the target air volume and guide angle of a zoned air curtain according to an embodiment of this disclosure. Figure 8 This is a block diagram of a dust prediction and air curtain zoning control device for a tunneling working face, according to an exemplary embodiment. Figure 9 This is an example schematic diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0020] This disclosure provides embodiments of a method, apparatus, electronic device, and storage medium for predicting dust and controlling air curtain zones at tunneling working faces. In some embodiments, the terms "method for predicting dust and controlling air curtain zones at tunneling working faces" can be interchanged with "information processing method" and "communication method," and the terms "apparatus for predicting dust and controlling air curtain zones at tunneling working faces" can be interchanged with "information processing device" and "communication device," and the terms "information processing system" and "communication system" can be interchanged.

[0021] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0022] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0023] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0024] In this disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular or a plural expression.

[0025] In the embodiments disclosed herein, "multiple" refers to two or more.

[0026] In some embodiments, the terms “at least one of,” “one or more,” “a plurality of,” and “multiple” may be used interchangeably.

[0027] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0028] In some embodiments, "terminal" or "terminal device" may be referred to as "user equipment (UE)," "user terminal," "mobile station (MS)," "mobile terminal (MT)," "subscriber station," "mobile unit," "subscriber unit," "wireless unit," "remote unit," "mobile device," "wireless device," "wireless communication device," "remote device," "mobile subscriber station," "access terminal," "mobile terminal," "wireless terminal," "remote terminal," "handset," "user agent," "mobile client," "client," etc.

[0029] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0030] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0031] In some embodiments, coal mine tunneling faces typically employ a ventilation and dust control method combining long-pressure short-extraction ventilation with air curtains, utilizing air curtains to block and guide dust diffusion. The air curtain is adjusted by setting up an air curtain generating structure and an airflow regulating device.

[0032] However, some control methods in certain embodiments rely on threshold-triggered adjustments based on real-time detection values ​​such as dust concentration, gas concentration, or wind speed. This is post-event feedback control, which struggles to respond promptly to dust diffusion trends caused by changes in the cutting position, resulting in adjustment lag. Some embodiments use overall airflow, overall air curtain intensity, or single outlet opening as adjustment targets, lacking independent analysis and zonal control of dust spatial distribution differences in different air curtain areas. This easily leads to insufficient local air curtain intensity or unreasonable airflow distribution. Furthermore, some embodiments fail to utilize pre-existing dust source information such as the cutting position, making it impossible to pre-adjust the airflow and guide angle of the corresponding area. Simultaneously, they do not adequately consider the impact of ventilation facility operating parameters such as main airflow velocity, air curtain airflow, guide angle, short-range negative pressure, and exhaust airflow on dust migration and extraction effectiveness, making it difficult to simultaneously achieve dust suppression, gas dilution, air curtain stability, and stable equipment operation.

[0033] Figure 1 This is a flowchart of the first method for dust prediction and air curtain zoning control at the tunneling working face provided in this disclosure embodiment, as follows: Figure 1 As shown, it includes the following steps: In step S11, multi-source status data of the tunneling face within a continuous time window are collected. The multi-source status data includes the working data of the tunneling face, the cutting position data, the operating parameters of the ventilation facilities, and the regional data of each air curtain's effective area. In some embodiments, the implementing entity of this disclosure may be, for example, an electronic device. This electronic device does not specifically refer to a particular fixed electronic device. For example, when the device identifier changes, the electronic device may also change accordingly. For example, when the structure of the electronic device changes, the electronic device may also change accordingly.

[0034] According to some embodiments, the tunneling face may be, for example, the foremost working area of ​​an underground roadway being excavated forward, wherein the tunneling face does not specifically refer to a fixed working area. For example, the tunneling face may also change accordingly when its geographical location changes.

[0035] In some embodiments, a continuous time window can be an uninterrupted, sequentially continuous duration. This continuous time window is not necessarily a fixed window. For example, when the time point corresponding to the continuous time window changes, the continuous time window can also change accordingly.

[0036] According to some embodiments, multi-source status data can be data collected from different devices, measuring points, or systems, and can be data corresponding to the tunneling face. This multi-source status data does not specifically refer to any fixed data. For example, when the method of acquiring the multi-source status data changes, the multi-source status data can also change accordingly. For example, when the time point at which the multi-source status data is acquired changes, the multi-source status data can also change accordingly.

[0037] According to some embodiments, the working data of the tunneling face may be data corresponding to the entire tunneling face, or working data collected when the tunneling face is in operation. The working data of the tunneling face does not specifically refer to any fixed data. For example, when the time point for acquiring the working data of the tunneling face changes, the working data of the tunneling face may also change accordingly. For example, when the tunneling face changes, the working data of the tunneling face may also change accordingly.

[0038] In some embodiments, the regional data for each air curtain's effective area can be data collected from each air curtain's effective area. This regional data for each air curtain's effective area does not refer to a specific fixed value. For example, when the air curtain's effective areas change, the regional data for each air curtain's effective area can also change accordingly. For example, when the method of acquiring the regional data for each air curtain's effective area changes, the regional data for each air curtain's effective area can also change accordingly.

[0039] In some embodiments, multi-source status data of the tunneling face can be collected within a continuous time window. This multi-source status data includes working data of the tunneling face, cutting position data, ventilation system operating parameters, and regional data of each air curtain's effective area. The cutting position data may include the current position of the cutting mechanism, the cutting direction, and the positional changes of the cutting mechanism within the continuous time window. The cutting mechanism may include the tunneling machine cutting head, the rock-breaking component at the end of the cutting arm, or other cutting components that can reflect changes in the location of dust sources. The ventilation system operating parameters may include at least one of the following: main airflow velocity, actual wind speed in each air curtain's effective area, air curtain volume, guide angle, short-circuit negative pressure, exhaust volume, and the relative position of the air curtain's effective area to the short-circuit inlet.

[0040] In step S12, the spatiotemporal feature data corresponding to the multi-source state data is obtained; In some embodiments, spatiotemporal feature data may refer, for example, to multi-source state data from different channels, which is deeply extracted, calculated, and refined from the temporal and spatial dimensions to generate feature information that reflects temporal change patterns and spatial location correlations. This spatiotemporal feature data does not specifically refer to any fixed data. For example, when the multi-source state data changes, the spatiotemporal feature data may also change accordingly.

[0041] According to some embodiments, spatiotemporal feature data corresponding to the multi-source state data can be obtained.

[0042] In step S13, a prediction model is used to identify the spatiotemporal feature data and obtain the state prediction result; According to some embodiments, the prediction model may be, for example, a model used to predict the tunneling face, and this prediction model is not specifically a fixed model. For example, the prediction model may also change when the model type changes. For example, the prediction model may also change when the model parameters change.

[0043] In some embodiments, the state prediction result can be, for example, the result obtained by predicting the tunneling face. This state prediction result is not specifically a fixed outcome. For example, the state prediction result may change accordingly when the prediction model changes. Similarly, the state prediction result may change accordingly when multi-source state data changes.

[0044] In step S14, under the condition that the set of operating conditions of the tunneling face satisfies the ventilation safety constraints and equipment operation constraints, according to the control target corresponding to the tunneling face, the MPC module is controlled to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operating parameters to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure. According to some embodiments, the set of operating conditions may be, for example, the set of operating conditions corresponding to the current tunneling face. This set of operating conditions may include at least one operating condition. Different tunneling faces may correspond to different sets of operating conditions. This set of operating conditions is not specifically a fixed set. For example, when the number of operating conditions corresponding to the set changes, the set of operating conditions may also change accordingly. For example, when a certain operating condition in the set changes, the set of operating conditions may also change accordingly.

[0045] In some embodiments, the target control quantity may be, for example, the acquired control quantity corresponding to the current control cycle. This target control quantity may also be referred to as a control quantity, adjustment quantity, etc. The target control quantity does not specifically refer to a fixed control quantity. For example, when the method of acquiring the target control quantity changes, the target control quantity may also change accordingly. When the control cycle changes, the target control quantity may also change accordingly. Specifically, when the duration of the control cycle changes, the control cycle may also change accordingly. For example, when the cycle identifier corresponding to the control cycle changes, the control cycle may also change accordingly.

[0046] According to some embodiments, under the condition that the set of operating conditions of the tunneling face satisfies ventilation safety constraints and equipment operation constraints, the MPC module can be controlled to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operating parameters according to the control target corresponding to the tunneling face, to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure.

[0047] In step S15, closed-loop compensation control is performed on the target actuator based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence. The target actuator includes at least one of the following: a forced-in fan, an extraction fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator.

[0048] In some embodiments, the feedback quantity can be, for example, data from the tunnel face. This feedback quantity does not specifically refer to a fixed data point. It can also be called feedback data. Furthermore, the feedback quantity can change as the time point at which it is acquired changes. For example, the feedback quantity can change as its specific value changes.

[0049] According to some embodiments, the target actuator may be, for example, an institution requiring closed-loop compensation control. The target actuator is not specifically defined as a single, fixed institution. For example, the target actuator may change when its name changes. Similarly, the target actuator may change when its identifier changes. Furthermore, the target actuator may change when its type changes.

[0050] According to some embodiments, the target actuator includes at least one of a forced-in fan, an exhaust fan, an air volume regulating mechanism, and a flow-directing angle actuator. The forced-in fan can be, for example, a mechanism that supplies air into the roadway, forcing fresh air into the working face under positive pressure. The exhaust fan can be, for example, a mechanism that extracts air outwards, directly exhausting polluted air, gas, and dust from the roadway. The air volume regulating mechanism can be, for example, a device that adjusts the ventilation volume. The flow-directing angle actuator can be, for example, an adjustable mechanism that adjusts the airflow direction and the air delivery angle.

[0051] In some or related embodiments, multi-source state data of the tunneling face within a continuous time window is collected. This multi-source state data includes working data, cutting position data, ventilation facility operating parameters, and regional data of each air curtain's effective area. Spatiotemporal feature data corresponding to the multi-source state data is obtained. A prediction model is used to identify the spatiotemporal feature data to obtain state prediction results. Under the condition that the set of operating conditions of the tunneling face satisfies ventilation safety constraints and equipment operating constraints, based on the control objective corresponding to the tunneling face, the MPC module is controlled to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data, and the ventilation facility operating parameters to obtain multiple candidate control sequences in the prediction time domain and target control quantities corresponding to each air curtain's effective area in the current control cycle. Closed-loop compensation control is performed on the target actuator based on the deviation between the target control quantity and the feedback quantity and the candidate control sequences. Therefore, by utilizing the dust source information and ventilation facility operating parameters, different air curtain action areas can be differentiated and controlled to reduce the problems of insufficient local air curtain intensity or unreasonable air volume distribution, thereby improving the stability of air curtain dust control and the accuracy of ventilation dust control.

[0052] Figure 2 This is a flowchart of the second method for dust prediction and air curtain zoning control at the tunneling working face provided in this disclosure embodiment, as follows: Figure 2 As shown, it includes the following steps: In step S21, multi-source status data of the tunneling face within a continuous time window are collected. The multi-source status data includes the working data of the tunneling face, the cutting position data, the operating parameters of the ventilation facilities, and the regional data of each air curtain action area. In some embodiments, the implementing entity of this disclosure may be, for example, an electronic device. This electronic device does not specifically refer to a particular fixed electronic device. For example, when the device identifier changes, the electronic device may also change accordingly. For example, when the structure of the electronic device changes, the electronic device may also change accordingly.

[0053] The relevant processes can be as described above, and will not be repeated here.

[0054] According to some embodiments, Figure 3 The diagram shown is an example schematic of a dust prediction and air curtain zoning control system for tunneling faces provided in an embodiment of this disclosure. Figure 3 As shown, the system may include a forced air supply unit, a main airflow regulation unit, a zoned air curtain regulation unit, a guide angle regulation unit, a short-range dust extraction unit, a detection unit 3, and a control unit. The forced air supply unit may be, for example, a forced air fan 11 used to deliver fresh air to the tunneling face; the main airflow regulation unit may be a main airflow regulation mechanism 16 used to regulate the main airflow required for face air supply and gas dilution; the zoned air curtain regulation unit may be an adjustable air curtain mechanism 17 used to adjust the corresponding air curtain airflow according to the dust conditions in different air curtain action areas; the guide angle regulation unit may be a guide angle actuator 18 used to adjust the air outlet direction of each air curtain action area; the short-range dust extraction unit may be an extraction fan 22 used to extract dust-laden airflow near the face; the detection unit is used to collect data such as dust, gas, wind speed, airflow, pressure difference, cutting mechanism position, and ventilation facility operating parameters; the control unit includes a data processing module 41, a CNN-LSTM prediction module 42, an MPC optimization module 43, a PID execution control module 44, and a control command output module 45. Based on the data collected by the detection unit, the control unit predicts future changes in operating conditions, calculates the target control quantity, and controls the operation of the main airflow adjustment unit, the zoned air curtain adjustment unit, the guide angle adjustment unit, and the short dust extraction unit.

[0055] In some embodiments, Figure 4 The diagram shown is an example schematic of a dust prediction and air curtain zoning control device for tunneling workfaces provided in an embodiment of this disclosure. Figure 4 As shown, it may include a tunneling face 100, a tunneling machine 1, a forced ventilation duct 2, a zoned adjustable air curtain control head 3, and a short exhaust duct 4.

[0056] In some embodiments, Figure 5 The diagram shown is an example schematic diagram of a method for dust prediction and air curtain zoning control at a tunneling working face provided by an embodiment of this disclosure, as follows: Figure 5 As shown, multi-source status data of the tunneling face can be collected through the detection unit. This multi-source status data may include dust, gas, wind speed, air volume, pressure difference, cutting position, and ventilation system operating parameters. Specifically, it may include, but is not limited to: (1) Dust concentration in each air curtain's effective area; (2) Dust concentration in the tunneling operation area; (3) Dust concentration on the return air side; (4) Gas concentration; (5) Main airflow speed; (6) Wind speed in the area affected by each wind curtain; (7) Negative pressure at the inlet of the short exhaust duct; (8) Ventilation facility operating parameters, including at least one of the following: air curtain volume, air guide angle, short exhaust negative pressure, exhaust volume and the relative position of the air curtain action area and the short exhaust inlet; (9) Cutting position information.

[0057] In step S22, the spatiotemporal feature data corresponding to the multi-source state data is obtained; The relevant processes can be as described above, and will not be repeated here.

[0058] In some embodiments, the control unit can preprocess the acquired multi-source state data. Preprocessing may include at least one of outlier removal, filtering, time synchronization, and normalization. The control unit can construct spatiotemporal feature data from data within a continuous time window. This spatiotemporal feature data includes spatial distribution information between different detection locations and dynamic information about the changes of each detection parameter over time. For example, it can be as shown in formula (1): (1) in, The dust concentration in each air curtain's effective area. The dust concentration behind the wind curtain. This refers to the dust concentration on the return air side. For gas concentration, Main airflow and wind speed, The wind speed in the area where each wind curtain is effective. For short-term negative pressure or pressure difference, These are the cut-off position parameters.

[0059] In step S23, a prediction model is used to identify the spatiotemporal feature data and obtain the state prediction result; The relevant processes can be as described above, and will not be repeated here.

[0060] According to some embodiments, the prediction model includes at least one of a CNN-LSTM model, an LSTM model, a GRU model, or a Transformer temporal model. Using the prediction model to identify the spatiotemporal feature data and obtain state prediction results may include: Extract the spatial distribution characteristics between each detection location in the tunneling face; The variation characteristics of the multi-source state data within a continuous time window are extracted, and the state prediction result is obtained based on the spatial distribution characteristics and the variation characteristics. Therefore, different spatiotemporal characteristics can be obtained through different models or modules, thereby improving the accuracy of the state prediction result.

[0061] In some embodiments, spatiotemporal feature data can be input into the prediction model. The prediction model may include at least one of a CNN-LSTM model, an LSTM model, a GRU model, or a Transformer time series model; when the prediction model includes a CNN-LSTM model, the CNN module is used to extract the spatial distribution features between each detection location, and the LSTM module is used to extract the dynamic change features in the continuous time series.

[0062] The CNN-LSTM prediction model outputs the predicted state value in the future prediction time domain, i.e., the state prediction result, as shown in Equation (2): (2) Among them, the predicted dust concentration is calculated for each air curtain operating area, the predicted dust concentration is calculated for the area behind the air curtain, the predicted dust concentration is calculated for the return air side, the predicted gas concentration is calculated, the predicted wind speed is calculated for each air curtain operating area, and the predicted short-term negative pressure or pressure difference is calculated. The predictive model can predict the short-term dust, gas, and airflow conditions, which can reduce the lag of simple threshold feedback control.

[0063] In step S24, under the condition that the set of operating conditions of the tunneling face satisfies the ventilation safety constraints and equipment operation constraints, according to the control target corresponding to the tunneling face, the MPC module is controlled to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operating parameters to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area, and the short-pump target negative pressure. The relevant processes can be as described above, and will not be repeated here.

[0064] According to some embodiments, Figure 6 The diagram shown is an example schematic of an MPC rolling optimization control method provided in an embodiment of this disclosure, such as... Figure 6 As shown, the MPC optimization module can calculate the target control quantity in the prediction time domain based on the state prediction results of the prediction model, the cut-off location data, and the operating parameters of the ventilation facility. The target control quantity can be expressed as shown in formula (3): (3) in, The target air volume for the main airflow. The target air volume for each air curtain's effective area. The guiding angle for the target area of ​​each wind curtain, The target negative pressure is for short-term pumping.

[0065] Specifically, the MPC optimization module can be controlled to solve for candidate control sequences with multiple control steps in the future prediction time domain within each control cycle, based on current detection data (multi-source state data), state prediction results, cutting position data, and ventilation facility operating parameters, and output only the control quantity corresponding to the current control cycle. The control cycle, prediction time domain, and control step size can be set according to the response time of the ventilation system at the tunneling face, sensor sampling frequency, and the response speed of the fan and actuator. After re-collecting data and updating the prediction results in the next control cycle, rolling optimization is performed again.

[0066] In some implementations, the MPC optimization objective can be determined: (1) Reduce dust concentration behind the air curtain and on the return air side; (2) Ensure that the gas concentration is below the safety limit; (3) The wind speed in the tunnel shall not be lower than the specified minimum wind speed requirement; (4) Maintain the stability of the wind curtain effect in each wind curtain area; (5) Ensure that the short-circuit negative pressure is within a reasonable working range; (6) Reduce the frequent and large-scale movements of the fan frequency, air volume adjustment mechanism and airflow angle actuator.

[0067] Alternatively, the MPC objective function can be expressed as shown in formulas (4)-(5):

[0068] (4) (5) in, The target value for dust control behind the air curtain. The target value for dust control on the return air side. For short-term negative pressure, To achieve short-term negative pressure, Let be the actual wind speed in the area where the i-th wind curtain is effective. Let i be the target wind speed in the area affected by the i-th wind curtain. For gas control target value, The target negative pressure is for short-term pumping. This is a metric for evaluating the effectiveness of the air curtain. Let Δ be the change in airflow in the area where the i-th wind curtain is applied. Let be the change in the guiding angle of the i-th wind curtain's effective area. a, b, c, d, e, f, and g are weighting coefficients.

[0069] In some implementations, MPC optimization should satisfy the following constraints: (1) The wind speed in the tunnel shall not be lower than the specified minimum wind speed requirement; (2) The gas concentration does not exceed the set safety limit; (3) The air volume in each air curtain's effective area is within the corresponding allowable range; (4) Each guide angle is within the mechanical limit range of the actuator; (5) The short-term negative pressure is within the set working range; (6) The frequencies of the intake fan and exhaust fan are within the rated operating range; (7) The rate of change of fan frequency, the rate of change of air volume regulating mechanism opening and the rate of change of guide angle shall not exceed the set upper limit; (8) Short-term negative pressure adjustment does not disrupt the main ventilation flow field of the tunneling face.

[0070] According to some embodiments, the method further includes: Based on the predicted dust concentration in each air curtain operating area, the total target air volume of the air curtain, the weight of each air curtain operating area, the dust generation position correction factor of the cutting mechanism relative to each air curtain operating area, and the ventilation effect correction factor, the target air volume corresponding to each air curtain operating area is obtained.

[0071] In some embodiments, Figure 7 The diagram shown is an example of a method for calculating the target airflow and guide angle of a zoned air curtain according to an embodiment of this disclosure. Figure 7 As shown, the target air volume for each air curtain's effective area can be determined based on the predicted dust concentration, dust generation location correction factor, ventilation effect correction factor, and area weight, for example, as shown in formula (6): (6) Where is the target air volume of the i-th air curtain's effective area, is the total target air volume of the air curtain, is the weighting coefficient of the i-th area, is the predicted dust concentration of the i-th area, is the dust generation position correction factor of the cutting mechanism relative to the i-th area, and μ is the dust generation position correction coefficient.

[0072] In the embodiment that introduces a ventilation effect correction factor, the control unit further corrects the target air volume based on the ventilation effect correction factor of the i-th region. The ventilation effect correction factor is used to reflect the influence of ventilation facility operating parameters such as main airflow velocity, air curtain air volume, guide angle, short-term negative pressure, and exhaust air volume on the dust migration, blocking, dilution, or exhaust effect in the air curtain area.

[0073] According to some embodiments, the method further includes: The dust generation location correction factor is determined based on the current position of the cutting mechanism, the cutting direction, the position change of the cutting mechanism within a continuous time window, and the spatial coverage of each wind curtain's effective area. Specifically, when the current position of the cutting mechanism is within the spatial coverage of the target wind curtain's effective area, or when it is determined based on the position change of the cutting mechanism within a continuous time window that it will enter the spatial coverage of the target wind curtain's effective area in the subsequent prediction time domain, the dust generation location correction factor corresponding to the target wind curtain's effective area is increased.

[0074] According to some embodiments, the ventilation effect correction factor is determined based on at least one of the following: main airflow velocity, actual wind speed in each air curtain area, air curtain volume, guide angle, short exhaust negative pressure, exhaust volume, and relative position between the air curtain area and the short exhaust inlet. It is used to characterize the influence of ventilation facility operating parameters on the dust migration, blocking, dilution, or exhaust effect in each air curtain area.

[0075] According to some embodiments, the dust generation location correction factor can be determined based on the current position of the cutting mechanism, the cutting direction, the positional change of the cutting mechanism within a continuous time window, and the spatial coverage of each air curtain's effective area. The spatial coverage of each air curtain's effective area characterizes the region within which the corresponding air curtain can effectively isolate, guide, or control airflow. When the current position of the cutting mechanism is within the spatial coverage of a certain air curtain's effective area, or when the positional change of the cutting mechanism within a continuous time window indicates that it will enter the spatial coverage of a certain air curtain's effective area in a subsequent short-term prediction time domain, it indicates that the air curtain's effective area is more likely to be affected by dust generation in the current or subsequent short-term prediction time domain, and the control unit increases the dust generation location correction factor for the corresponding air curtain's effective area.

[0076] According to some embodiments, the dust concentration in each air curtain's effective area is affected not only by dust source factors such as the current position of the cutting mechanism, the cutting direction, and changes in the cutting mechanism's position, but also by ventilation facility operating parameters such as the main airflow velocity, air curtain volume, guide angle, short-extraction negative pressure, exhaust volume, and the relative position of the air curtain's effective area and the short-extraction inlet. Therefore, when determining the target airflow and guide angle for each air curtain's effective area, the control unit simultaneously introduces a dust generation location correction factor and a ventilation effect correction factor. The dust generation location correction factor characterizes the degree of influence of dust source location changes on each air curtain's effective area, while the ventilation effect correction factor characterizes the degree of influence of ventilation facility operating parameters on dust migration, blocking, dilution, and extraction effects.

[0077] Specifically, when the current position of the cutting mechanism corresponds to a certain air curtain action area, the dust generation position correction factor corresponding to that area increases; when the cutting mechanism is in the transition range of two adjacent air curtain action areas, or when the position change of the cutting mechanism within a continuous time window indicates that it will pass through two adjacent air curtain action areas, the dust generation position correction factors corresponding to multiple air curtain action areas can be increased according to the degree of influence.

[0078] According to some embodiments, the control unit determines the zone control weight of each air curtain action area based on the predicted dust concentration, dust generation location correction factor and ventilation effect correction factor, and performs rolling optimization of the target air volume and target guide angle of each air curtain action area through the MPC module based on the zone control weight, so that the system can not only perform feedback adjustment based on the predicted dust concentration value, but also perform feedforward pre-adjustment of one or more corresponding air curtain action areas based on the dust source front information and ventilation engineering effect.

[0079] According to some embodiments, the method further includes: Based on the predicted dust concentration in each air curtain operating area, the wind speed in each air curtain operating area, the dust generation position correction factor of the cutting mechanism relative to each air curtain operating area, and the ventilation effect correction factor, the guiding target angle corresponding to each air curtain operating area is obtained.

[0080] According to some embodiments, the guiding target angle of each air curtain action area is determined based on the predicted dust concentration, the cut-off position, the wind speed in the corresponding area, and the ventilation effect correction factor, for example, as shown in formula (7): (7) Wherein, is the target guiding angle of the i-th wind curtain area, is the initial guiding angle, is the predicted dust concentration of the i-th area, is the dust control target value of the i-th area, is the correction factor for the dust generation impact of the cutting position on the i-th wind curtain area, is the actual wind speed of the i-th area, is the target wind speed of the i-th area, and the relevant correction coefficients are used to adjust the degree of influence of different factors on the guiding target angle.

[0081] In the embodiment that introduces a ventilation effect correction factor, the guiding target angle can be further corrected according to the ventilation effect correction factor T_i of the i-th region to reflect the influence of ventilation facility operating parameters such as main airflow velocity, air curtain volume, guiding angle, short-extraction negative pressure and exhaust volume on the dust migration direction.

[0082] When one or more air curtain action areas are affected by the cutting operation location, the control unit can adjust the guiding target angle of the above areas according to the dust generation location correction factor, ventilation effect correction factor, predicted dust concentration and wind speed status of the corresponding area, so that the air curtain airflow is output in a direction that is conducive to suppressing dust escape and guiding the dust-laden airflow into the short extraction area.

[0083] In step S25, closed-loop compensation control is performed on the target actuator based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence. The target actuator includes at least one of the following: a forced-in fan, an extraction fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator. The relevant processes can be as described above, and will not be repeated here.

[0084] According to some embodiments, the step of performing closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity includes: A PID model is employed to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity. Therefore, through PID-based low-level closed-loop compensation, the target airflow, target guide angle, and target short-range negative pressure can more stably track the actual actuator, reducing adjustment deviations.

[0085] In some embodiments, after the MPC outputs the target control value, the PID execution control module can perform tracking control on the actuator based on the deviation between the target value and the actual feedback value.

[0086] (8) (9) in, Let i be the target air volume for the i-th region. Let i be the actual air volume in the i-th region. Kp, Ki, and Kd are the control variables for the airflow regulation mechanism in the i-th zone, and Kp, Ki, and Kd are the PID parameters.

[0087] Similarly, the PID control module can be used for tracking control of main airflow volume, guide angle, short-circuit negative pressure, and fan frequency.

[0088] According to some embodiments, the control unit controls the actuator's action based on the PID output result, including at least one of the following: (1) Adjust the frequency of the forced air blower or the main airflow regulating mechanism to ensure that the wind speed at the tunneling face meets the minimum wind speed requirements and the gas dilution requirements; (2) Adjust each adjustable air curtain mechanism to make the corresponding air curtain action area reach the target air volume; (3) Adjust the actuators of each airflow guide angle so that the corresponding air curtain action area reaches the target air outlet direction; (4) Adjust the frequency of the extraction fan to keep the short-term negative pressure within a reasonable range and match it with the main airflow and the air curtain airflow.

[0089] In some embodiments, after performing adjustments, the control unit continues to collect data on dust concentration, gas concentration, wind speed, air volume, short-circuit negative pressure, ventilation facility operating parameters, and cutting mechanism position. The updated data is then input into the prediction model for the next control cycle. By continuously executing these steps, a closed-loop control system for predicting, optimizing, executing, and providing feedback on the ventilation and dust control status of the tunneling face can be achieved.

[0090] In step S26, the air curtain effect status evaluation corresponding to the tunneling face is obtained according to the status evaluation parameter set and the weights of each status evaluation parameter in the status evaluation parameter set. The target air volume and / or target guide angle for the next control cycle are corrected according to the air curtain effect status evaluation. The status evaluation parameter set includes at least one of the following: dust concentration behind the air curtain, dust concentration on the return air side, short-run negative pressure deviation, and zoned air curtain wind speed deviation.

[0091] In some embodiments, the state evaluation parameter set may include, for example, a collection of at least one state evaluation parameter. This state evaluation parameter set is not specifically a fixed set. For example, when a parameter in the state evaluation parameter set changes, the state evaluation parameter set may also change accordingly. For example, when the amount of data corresponding to the state evaluation parameter set changes, the state evaluation parameter set may also change accordingly.

[0092] A block diagram illustrating a method for dust prediction and air curtain zoning control at a tunneling working face, according to an exemplary embodiment. (Refer to...) Figure 8 The device 800 includes: The data acquisition unit 801 is used to acquire multi-source status data of the tunneling face within a continuous time window. The multi-source status data includes the working data of the tunneling face, the cutting position data, the operating parameters of the ventilation facilities, and the regional data of each air curtain action area. The data acquisition unit 801 is also used to acquire spatiotemporal feature data corresponding to the multi-source state data; The result acquisition unit 802 is used to identify the spatiotemporal feature data using a prediction model and obtain the state prediction result; The control quantity acquisition unit 803 is used to control the MPC module to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operation parameters according to the control target corresponding to the tunneling face, under the condition that the set of operating conditions of the tunneling face meets the ventilation safety constraints and equipment operation constraints, and to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure. The mechanism control unit 804 is used to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence, wherein the target actuator includes at least one of the following: a forced-in fan, an exhaust fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator.

[0093] According to some embodiments, the mechanism control unit 804, when performing closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity, is specifically used for: A PID model is used to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity.

[0094] According to some embodiments, the prediction model includes at least one of a CNN-LSTM model, an LSTM model, a GRU model, or a Transformer temporal model; when the prediction model includes a CNN-LSTM model, the result acquisition unit 802, used to identify the spatiotemporal feature data using the prediction model and obtain a state prediction result, may include: Extract the spatial distribution characteristics between each detection location in the tunneling face; Extract the variation characteristics of the multi-source state data within a continuous time window, and obtain the state prediction result based on the spatial distribution characteristics and the variation characteristics.

[0095] According to some embodiments, the control quantity acquisition unit 803 is further specifically used for: Based on the predicted dust concentration in each air curtain's effective area, the total target air volume of the air curtain, the weight of each air curtain's effective area, the dust generation position correction factor of the cutting mechanism relative to each air curtain's effective area, and the ventilation effect correction factor, the target air volume corresponding to each air curtain's effective area is obtained.

[0096] According to some embodiments, the control quantity acquisition unit 803 is further specifically used for: Based on the predicted dust concentration in each air curtain operating area, the wind speed in each air curtain operating area, the dust generation position correction factor of the cutting mechanism relative to each air curtain operating area, and the ventilation effect correction factor, the guiding target angle corresponding to each air curtain operating area is obtained.

[0097] According to some embodiments, the control quantity acquisition unit 803 is further specifically used for: The dust generation location correction factor is determined based on the current position of the cutting mechanism, the cutting direction, the position change of the cutting mechanism within a continuous time window, and the spatial coverage of each wind curtain's effective area. Specifically, when the current position of the cutting mechanism is within the spatial coverage of the target wind curtain's effective area, or when it is determined based on the position change of the cutting mechanism within a continuous time window that it will enter the spatial coverage of the target wind curtain's effective area in the subsequent prediction time domain, the dust generation location correction factor corresponding to the target wind curtain's effective area is increased.

[0098] According to some embodiments, the ventilation effect correction factor is determined based on at least one of the following: main airflow velocity, actual wind speed in each air curtain area, air curtain volume, guide angle, short exhaust negative pressure, exhaust volume, and relative position between the air curtain area and the short exhaust inlet. It is used to characterize the influence of ventilation facility operating parameters on the dust migration, blocking, dilution, or exhaust effect in each air curtain area.

[0099] According to some embodiments, the control quantity acquisition unit 803 is further specifically used for: Based on the set of status evaluation parameters and the weights corresponding to each status evaluation parameter in the set of status evaluation parameters, the status evaluation of the air curtain effect corresponding to the tunneling face is obtained, and the target air volume and / or target guide angle for the next control cycle are corrected based on the status evaluation of the air curtain effect. The set of status evaluation parameters includes at least one of the following: dust concentration behind the air curtain, dust concentration on the return air side, short-run negative pressure deviation, and zoned air curtain wind speed deviation.

[0100] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0101] Figure 9A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device 900 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0102] like Figure 9 As shown, the electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded into a random access memory (RAM) 903 from a storage unit 908. The RAM 903 may also store various programs and data required for the operation of the electronic device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0103] Multiple components in electronic device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of displays, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows electronic device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0104] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above. For example, in some embodiments, the above methods can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the above methods by any other suitable means (e.g., by means of firmware).

[0105] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0108] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0109] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0110] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0111] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0112] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for dust prediction and air curtain zoning control at a tunneling working face, characterized in that, include: Collect multi-source status data of the tunneling face within a continuous time window, wherein the multi-source status data includes the working data of the tunneling face, cutting position data, ventilation facility operation parameters, and regional data of each air curtain action area; Obtain the spatiotemporal feature data corresponding to the multi-source state data; A prediction model is used to identify the spatiotemporal feature data and obtain state prediction results, which include the predicted dust concentration and / or predicted wind speed in each wind curtain area. Under the condition that the set of operating conditions of the tunneling face satisfies the ventilation safety constraints and equipment operation constraints, according to the control target corresponding to the tunneling face, the MPC module is controlled to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operation parameters to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure. Based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence, closed-loop compensation control is performed on the target actuator, wherein the target actuator includes at least one of the following: an inlet fan, an outlet fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator.

2. The method according to claim 1, characterized in that, The step of performing closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity includes: A PID model is used to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity.

3. The method according to claim 1 or 2, characterized in that, The prediction model includes at least one of CNN-LSTM model, LSTM model, GRU model, or Transformer temporal model. The step of using the prediction model to identify the spatiotemporal feature data and obtain state prediction results includes: Extract the spatial distribution characteristics between each detection location in the tunneling face; Extract the variation characteristics of the multi-source state data within a continuous time window, and obtain the state prediction result based on the spatial distribution characteristics and the variation characteristics.

4. The method according to claim 1, characterized in that, The method further includes: Based on the predicted dust concentration in each air curtain's effective area, the total target air volume of the air curtain, the weight of each air curtain's effective area, the dust generation position correction factor of the cutting mechanism relative to each air curtain's effective area, and the ventilation effect correction factor, the target air volume corresponding to each air curtain's effective area is obtained.

5. The method according to claim 1, characterized in that, The method further includes: Based on the predicted dust concentration in each air curtain operating area, the wind speed in each air curtain operating area, the dust generation position correction factor of the cutting mechanism relative to each air curtain operating area, and the ventilation effect correction factor, the guiding target angle corresponding to each air curtain operating area is obtained.

6. The method according to claim 4 or 5, characterized in that, The method further includes: The dust generation location correction factor is determined based on the current position of the cutting mechanism, the cutting direction, the position change of the cutting mechanism within a continuous time window, and the spatial coverage of each wind curtain's effective area. Specifically, when the current position of the cutting mechanism is within the spatial coverage of the target wind curtain's effective area, or when it is determined based on the position change of the cutting mechanism within a continuous time window that it will enter the spatial coverage of the target wind curtain's effective area in the subsequent prediction time domain, the dust generation location correction factor corresponding to the target wind curtain's effective area is increased.

7. The method according to claim 4 or 5, characterized in that, The ventilation effect correction factor is determined based on at least one of the following: main airflow velocity, actual wind speed in each air curtain area, air curtain volume, guide angle, short exhaust negative pressure, exhaust volume, and relative position between the air curtain area and the short exhaust inlet. It is used to characterize the influence of ventilation facility operating parameters on the dust migration, blocking, dilution, or exhaust effect in each air curtain area.

8. The method according to claim 1, characterized in that, The method further includes: Based on the set of status evaluation parameters and the weights corresponding to each status evaluation parameter in the set of status evaluation parameters, the status evaluation of the air curtain effect corresponding to the tunneling face is obtained, and the target air volume and / or target guide angle for the next control cycle are corrected based on the status evaluation of the air curtain effect. The set of status evaluation parameters includes at least one of the following: dust concentration behind the air curtain, dust concentration on the return air side, short-run negative pressure deviation, and zoned air curtain wind speed deviation.

9. A method for dust prediction and air curtain zoning control at a tunneling working face, characterized in that, include: The data acquisition unit is used to acquire multi-source status data of the tunneling face within a continuous time window. The multi-source status data includes the working data of the tunneling face, the cutting position data, the operating parameters of the ventilation facilities, and the regional data of each air curtain's effective area. The data acquisition unit is also used to acquire spatiotemporal feature data corresponding to the multi-source state data; The result acquisition unit is used to identify the spatiotemporal feature data using a prediction model and obtain the state prediction result. The control quantity acquisition unit is used to control the MPC module to perform rolling optimization processing on the multi-source state data, the state prediction results, the cutting position data and the ventilation facility operation parameters according to the control target corresponding to the tunneling face, under the condition that the set of operating conditions of the tunneling face meets the ventilation safety constraints and equipment operation constraints, and to obtain multiple candidate control sequences in the prediction time domain and the target control quantities corresponding to each air curtain action area in the current control cycle. The target control quantities include at least one of the following: the main airflow target control quantity, the target air volume of each air curtain action area, the target guide angle of each air curtain action area and the short-pump target negative pressure. The mechanism control unit is used to perform closed-loop compensation control on the target actuator based on the deviation between the target control quantity and the feedback quantity and the candidate control sequence, wherein the target actuator includes at least one of the following: an inlet fan, an outlet fan, an air volume regulating mechanism, an air curtain generating mechanism, and a guide angle actuator.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement a method for predicting dust and controlling air curtain zones at a tunneling working face as described in any one of claims 1 to 8.

Images