Intelligent air regulation and control method and device for large mineral separation workshop

Abstract

The invention provides an air regulation and control device and method for a mineral separation workshop, electronic equipment and a storage medium, and relates to the technical field of air regulation and control. The air regulation and control device of the mineral separation workshop comprises a fan assembly, a skylight assembly, an environmental parameter monitoring assembly and an intelligent fresh air control system. The draught fan assembly comprises a plurality of draught fans, and the draught fans are used for supplying air to the second space area from the first space area. The skylight assembly comprises a plurality of skylights, the opening degree of the skylights is adjustable, the skylights are used for being communicated with the outside, and the horizontal height of the skylight assembly is larger than that of the second space area. The environmental parameter monitoring assembly comprises a plurality of air quality monitoring sensors, and the air quality monitoring sensors are used for monitoring environmental parameters in the ore dressing workshop. The intelligent fresh air control system is electrically connected with the skylight assembly, the fan assembly and the environment parameter monitoring assembly, and the intelligent fresh air control system controls the skylight assembly and the fan assembly to work according to environment parameters monitored by the environment parameter monitoring assembly.

Description

Technical Field

[0001] The present application relates to the technical field of air control, and in particular to an air control device, an air control method, an electronic device and a storage medium for a mineral processing workshop. Background Art

[0002] In order to ensure that the flotation process is not affected by freezing, in winter, especially in extremely cold areas, super-large mineral processing plants adopt closed building design, placing mineral processing equipment in closed buildings, and conducting mineral processing inside the buildings. As a result, the flotation workshop is poorly ventilated, and a large amount of high-temperature flotation gas, mineral processing agent odor, and dust generated by flotation foam rupture gather indoors, which seriously threatens the occupational health of workshop operators.

[0003] In summer, the outdoor temperature rises, causing the temperature inside the flotation workshop to increase. The workshop temperature exceeds 40°C. The odor and dust of flotation agents further deteriorate the working environment of employees in the workshop. Operators need to wear gas masks to work, and production conditions are poor.

[0004] At present, traditional industrial ventilation methods mainly include natural ventilation and mechanical ventilation. Natural ventilation is to make air flow under the combined action of wind pressure and heat pressure, without consuming mechanical power, and is widely used as a relatively economical ventilation method. However, the internal space of the ore dressing plant building is large, the degree of airtightness is high, and there are many flotation machinery and equipment, forming a large number of ventilation dead zones in the workshop, and it is impossible to complete effective ventilation of the workshop through mechanical ventilation.

[0005] The traditional cooling method mainly uses air conditioning. In the flotation workshop where a large amount of hot air is injected, air conditioning cooling will require huge energy and air conditioning equipment. Summary of the invention

[0006] In view of this, the present application provides an air control device, an air control method, an electronic device and a storage medium for a mineral processing workshop.

[0007] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect, the present application provides an air control device for a mineral processing workshop, comprising: a fan assembly, a skylight assembly, an environmental parameter monitoring assembly and an intelligent fresh air control system. The fan assembly includes a plurality of fans, and the fans are used to supply air from a first space area to a second space area; wherein the horizontal height of the first space area is lower than the horizontal height of the second space area; the skylight assembly includes a plurality of skylights, the opening degree of the skylights is adjustable, and is used to communicate with the outside world, and the horizontal height of the skylight assembly is higher than the second space area. The environmental parameter monitoring assembly includes a plurality of air quality monitoring sensors, and the air quality monitoring sensors are used to monitor the environmental parameters in the mineral processing workshop. The intelligent fresh air control system is electrically connected to the skylight assembly, the fan assembly and the environmental parameter monitoring assembly, and the intelligent fresh air control system controls the operation of the skylight assembly and the fan assembly according to the environmental parameters monitored by the environmental parameter monitoring assembly.

[0008] The air control device of the ore dressing workshop of the embodiment of the present application, by setting a fan assembly, a skylight assembly and an environmental parameter monitoring assembly in the ore dressing workshop, the intelligent fresh air control system can control the skylight assembly and the fan assembly to work according to the environmental parameters monitored by the environmental parameter monitoring assembly, so that when the temperature of the ore dressing workshop is high, the cold air in the first space area can be transported to the second space area through the fan, which can achieve the cooling of the ore dressing workshop, and can solve the problem of alarm and production failure caused by local high temperature of workshop machinery and equipment in production. And because the energy consumption of the fan is low, the operating cost of the ore dressing workshop can be reduced. At the same time, the fan can drive the flow of gas in the ore dressing workshop, and the skylight can connect the ore dressing workshop with the outside world, so that the airflow can take away the hot air, flotation odor and dust discharged by the flotation machine from the ore dressing workshop, which is conducive to protecting the occupational health of the staff.

[0009] In some embodiments, the air quality monitoring sensor includes a dust concentration sensor, a temperature sensor, a flotation odor concentration sensor and a humidity sensor. The dust concentration sensor is used to monitor the dust concentration in the mineral processing workshop, the temperature sensor is used to monitor the temperature in the mineral processing workshop, the flotation odor concentration sensor is used to monitor the flotation odor concentration in the mineral processing workshop, and the humidity sensor is used to monitor the humidity in the mineral processing workshop.

[0010] In a second aspect, the present application provides an air control method for a mineral processing workshop, which is applied to the air control device of the mineral processing workshop. The air control method for the mineral processing workshop includes: collecting environmental parameters in the mineral processing workshop through an environmental parameter monitoring component. Preprocessing the collected environmental parameters to obtain preprocessed environmental data. Inputting the obtained preprocessed environmental data into an intelligent fresh air control system, and calculating a control strategy through the intelligent fresh air control system. Controlling the operation of the fan component and the skylight component according to the control strategy calculated by the intelligent fresh air control system.

[0011] In some embodiments, the collected environmental parameters are preprocessed to obtain preprocessed environmental data, including: determining outliers in the environmental parameters through a local anomaly factor algorithm; calculating the mean after removing the outliers; adding the mean to the environmental parameters after removing the outliers to obtain environmental data; normalizing the environmental data; and synthesizing the processed environmental parameters into a state vector to obtain preprocessed environmental data.

[0012] In some embodiments, determining outliers in environmental parameters through a local anomaly factor algorithm includes: for each data point in the environmental parameter, calculating the k-distance of each data point; based on the k-distance, calculating the reachable distance; based on the reachable distance, calculating the local reachable density; based on the reachable density, calculating the local anomaly factor; based on the local anomaly factor, determining whether each data point is an outlier.

[0013] In some embodiments, the air control method for a mineral processing workshop further includes: collecting environmental parameters in the mineral processing workshop through an environmental parameter monitoring component while collecting the start / stop status and operating frequency of each fan, as well as the opening degree of the skylight.

[0014] In some embodiments, the obtained preprocessed environmental data is input into an intelligent fresh air control system, and the control strategy is calculated by the intelligent fresh air control system, including: inputting the obtained preprocessed environmental data into a pre-trained proximal strategy optimization model; the proximal strategy optimization model calculates the control strategy and generates control instructions for the fan and skylight.

[0015] In some embodiments, the work of controlling the fan component and the skylight component according to the control strategy calculated by the intelligent fresh air control system also includes: converting the control instructions of the fan and the skylight generated by the proximal strategy optimization model into actual control signals; controlling the opening or closing of the fan, the operating frequency of the fan and the opening of the skylight through the actual control signals.

[0016] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor, the memory storing computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the above-mentioned air control method for the mineral processing workshop.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When the computer execution instructions are executed by a processor, they are used to implement the above-mentioned air control method for a mineral processing workshop.

[0018] Among them, the technical effects brought about by any design method in the second aspect, the third aspect, and the fourth aspect can refer to the technical effects brought about by different design methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A front view of an air conditioning device for a mineral processing workshop provided in some embodiments of the present application; Figure 2 A side view of an air conditioning device for a mineral processing workshop provided in some embodiments of the present application; Figure 3 A top view of an air conditioning device for a mineral processing workshop provided in some embodiments of the present application; Figure 4 A schematic diagram of the composition of an electronic device provided in an embodiment of the present application.

[0020] Reference numerals: 100. electronic device; 101. control unit; 102. determination unit; 103. processing module; 1031. processor; 104. communication module; 1041. communication bus; 1042. communication interface; 105. storage module; 1051. memory; 200. mineral processing workshop; 201. flotation column; 202. first space area; 203. second space area; 300. air control device; 301. fan assembly; 302. skylight assembly. DETAILED DESCRIPTION

[0021] In the embodiments of the present application, the terms "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0022] In the description of the embodiments of the present application, the term "and / or" refers to and covers any and all possible combinations of one or more of the associated listed items. The term "and / or" is a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present application generally indicates that the associated objects before and after are in an "or" relationship.

[0023] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, "connection" can be a detachable connection or a non-detachable connection; it can be a direct connection or an indirect connection through an intermediate medium.

[0024] In the description of the embodiments of the present application, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0025] In order to ensure that the flotation process is not affected by freezing, in winter, especially in extremely cold areas, super-large mineral processing plants adopt closed building design, placing mineral processing equipment in closed buildings, and conducting mineral processing inside the buildings. As a result, the flotation workshop is poorly ventilated, and a large amount of high-temperature flotation gas, mineral processing agent odor, and dust generated by flotation foam rupture gather indoors, which seriously threatens the occupational health of workshop operators.

[0026] In summer, the outdoor temperature rises, causing the temperature inside the flotation workshop to increase. The workshop temperature exceeds 40°C. The odor and dust of flotation agents further deteriorate the working environment of employees in the workshop. Operators need to wear gas masks to work, and production conditions are poor.

[0027] At present, traditional industrial ventilation methods mainly include natural ventilation and mechanical ventilation. Natural ventilation is to make air flow under the combined action of wind pressure and heat pressure, without consuming mechanical power, and is widely used as a relatively economical ventilation method. However, the internal space of the ore dressing plant building is large, the degree of airtightness is high, and there are many flotation machinery and equipment, forming a large number of ventilation dead zones in the workshop, and it is impossible to complete effective ventilation of the workshop through mechanical ventilation.

[0028] The traditional cooling method mainly uses air conditioning. In the flotation workshop where a large amount of hot air is injected, air conditioning cooling will require huge energy and air conditioning equipment.

[0029] In order to solve the above technical problems, the present application provides an air control device and method for a mineral processing workshop.

[0030] See also Figure 1-Figure 3 , Figure 1 A front view of an air conditioning device for a ore dressing workshop provided in some embodiments of the present application, Figure 2 A side view of an air conditioning device for a mineral processing workshop provided in some embodiments of the present application, Figure 3A top view of an air control device of a mineral processing workshop provided in some embodiments of the present application. The mineral processing workshop 200 may have a first space area 202 and a second space area 203. In the height direction of the mineral processing workshop 200, the horizontal height of the first space area 202 is lower than the horizontal height of the second space area 203. The air control device 300 of the mineral processing workshop 200 includes a fan assembly 301, a skylight assembly 302, an environmental parameter monitoring assembly (not shown in the figure) and an intelligent fresh air control system (not shown in the figure).

[0031] The fan assembly 301 may include a plurality of fans, wherein "plurality" means that the number of fans is two or more. Exemplarily, the plurality of fans may be arranged at intervals at the bottom of the ore dressing workshop 200, and the number of fans may be 10 or more, wherein the top of the ore dressing workshop 200 is directly opposite to the bottom of the ore dressing workshop 200.

[0032] The fan is used to supply air from the first space area 202 to the second space area 203. Specifically, the second space area 203 can be used as a working space, and the second space area 203 can be provided with flotation columns 201, workbenches and other components. Since the height of the second space area 203 is relatively high (for example, it can reach 38 meters), there is no operating process in the first space area 202, it is adjacent to the ground, and there is no light exposure, the temperature in the first space area 202 is relatively low. Among them, the temperature in the first space area 202 can be 10°C lower than the temperature of the external environment. Therefore, the air inlet of the fan absorbs the cold air of the first space area 202, and the air outlet of the fan can be directly opposite to the second space area 203, so that the cold air in the first space area 202 can be transported to the second space area 203, so that the air in the ore dressing workshop 200 can flow, and the ore dressing workshop 200 can be cooled without cooling.

[0033] For example, there is a dead zone of wind flow in the ore dressing workshop 200. The dead zone of wind flow is a relatively closed or semi-closed area surrounded by the walls, equipment, etc. of the ore dressing workshop 200, which is not conducive to the flow of air, or the air flow will form a vortex in this area. Then, the fan can be installed in the area of ​​the ore dressing workshop 200 where the dead zone of wind flow is easy to form, so as to achieve the cooling of the ore dressing workshop 200 and drive the flow of air flow in the dead zone of wind flow, thereby achieving the flow of air flow in the entire ore dressing workshop 200.

[0034] The skylight assembly 302 is higher than the second space area 203. For example, the skylight assembly 302 can be arranged on the top of the mineral processing workshop 200.

[0035] The skylight assembly 302 may include a plurality of skylights. The skylights are used to communicate with the outside world, so that the hot air discharged from the flotation machine in the ore dressing workshop 200, the flotation odor, and the dust generated by the flotation foam bursting can flow to the outside world through the skylights.

[0036] The opening degree of the sunroof is adjustable. The sunroof can be opened by sliding, rotating, etc.

[0037] The environmental parameter monitoring component may include a plurality of air quality monitoring sensors. The air quality monitoring sensors may be used to monitor environmental parameters in the ore dressing workshop 200. For example, the air quality monitoring sensors may be used to detect temperature, humidity, flotation odor, etc. By providing air quality monitoring sensors, the environmental parameters in the ore dressing workshop 200 may be monitored in real time.

[0038] Exemplarily, the air quality monitoring sensor may be installed on a workbench on the upper part of the flotation column 201, and there is a distance between the air quality monitoring sensor and the flotation column 201. The distance between the air quality monitoring sensor and the flotation column 201 may be 1-1.5 m.

[0039] The intelligent fresh air control system is electrically connected to the skylight assembly 302, the fan assembly 301 and the environmental parameter monitoring assembly. The intelligent fresh air control system can control the skylight assembly 302 and the fan assembly 301 to work according to the environmental parameters monitored by the environmental parameter monitoring assembly. Specifically, the environmental parameter information monitored by the environmental parameter monitoring assembly can be processed by the intelligent fresh air control system to obtain a control command, so that the fan assembly 301 and the skylight assembly 302 can be controlled, that is, the opening or closing of the fan, the operating frequency of the fan, the opening of the skylight, and other actions can be controlled.

[0040] According to the air control device 300 of the ore dressing workshop 200 of the embodiment of the present application, by setting the fan assembly 301, the skylight assembly 302 and the environmental parameter monitoring assembly in the ore dressing workshop 200, the intelligent fresh air control system can control the skylight assembly 302 and the fan assembly 301 to work according to the environmental parameters monitored by the environmental parameter monitoring assembly, so that when the temperature of the ore dressing workshop 200 is high, the cold air in the first space area 202 can be transported to the second space area 203 through the fan, so that the ore dressing workshop 200 can be cooled down, and the alarm and production failure problems caused by local high temperature of workshop machinery and equipment in production can be solved. And because the energy consumption of the fan is low, the operating cost of the ore dressing workshop 200 can be reduced. At the same time, the fan can drive the flow of gas in the ore dressing workshop 200, and the skylight can connect the ore dressing workshop 200 with the outside world, so that the airflow can take the hot air, flotation odor and dust discharged by the flotation machine away from the ore dressing workshop 200, which is conducive to protecting the occupational health of the staff.

[0041] Please continue reading Figure 1-Figure 3In some embodiments, the air quality monitoring sensor may include a dust concentration sensor, a temperature sensor, a flotation odor concentration sensor, and a humidity sensor. The dust concentration sensor is used to monitor the dust concentration in the mineral processing workshop 200. The temperature sensor is used to monitor the temperature in the mineral processing workshop 200, the flotation odor sensor is used to monitor the flotation odor concentration in the mineral processing workshop 200, and the humidity sensor is used to monitor the humidity in the mineral processing workshop 200. Among them, the dust concentration sensor has an accuracy of not less than 0.1ug / m 3 , the temperature sensor accuracy is not less than 0.1°C, the flotation odor concentration sensor accuracy is not less than 100 ppm, and the humidity sensor accuracy is not less than 0.1%. By monitoring the dust concentration, temperature, flotation odor concentration and humidity in the ore dressing workshop 200, the environmental parameters in the ore dressing workshop 200 can be monitored more comprehensively, so that the fan assembly 301 and the skylight assembly 302 can be controlled more scientifically.

[0042] The air control method of the ore dressing workshop 200 according to the embodiment of the present application is described below.

[0043] The air control method of the ore dressing workshop 200 comprises the following steps: S1: Collect environmental parameters in the ore dressing workshop 200 through the environmental parameter monitoring component. Specifically, the collected environmental parameters can be temperature T, flotation odor concentration C, dust concentration D and humidity H. Among them, the flotation odor concentration in the room 200 in the ore dressing workshop 200, and the humidity sensor is used to monitor the humidity in the ore dressing workshop 200. Among them, the dust concentration sensor has an accuracy of not less than 0.1ug / m 3 , the temperature sensor accuracy is not less than 0.1°C, the flotation odor concentration sensor accuracy is not less than 100 ppm, and the humidity sensor accuracy is not less than 0.1%. By monitoring the dust concentration, temperature, flotation odor concentration and humidity in the ore dressing workshop 200, the environmental parameters in the ore dressing workshop 200 can be monitored more comprehensively, so that the fan assembly 301 and the skylight assembly 302 can be controlled more scientifically.

[0044] The air control method of the ore dressing workshop 200 according to the embodiment of the present application is described below.

[0045] The air control method of the ore dressing workshop 200 comprises the following steps: S1: Collect environmental parameters in the ore dressing workshop 200 through the environmental parameter monitoring component. Specifically, the collected environmental parameters can be temperature T, flotation odor concentration C, dust concentration D and humidity H. Among them, the flotation odor concentration in the room 200 in the ore dressing workshop 200, and the humidity sensor is used to monitor the humidity in the ore dressing workshop 200. Among them, the dust concentration sensor has an accuracy of not less than 0.1ug / m 3, the temperature sensor accuracy is not less than 0.1°C, the flotation odor concentration sensor accuracy is not less than 100 ppm, and the humidity sensor accuracy is not less than 0.1%. By monitoring the dust concentration, temperature, flotation odor concentration and humidity in the ore dressing workshop 200, the environmental parameters in the ore dressing workshop 200 can be monitored more comprehensively, so that the fan assembly 301 and the skylight assembly 302 can be controlled more scientifically.

[0046] The air control method of the ore dressing workshop 200 according to the embodiment of the present application is described below.

[0047] The air control method of the ore dressing workshop 200 comprises the following steps: S1: The environmental parameters in the ore dressing workshop 200 are collected by the environmental parameter monitoring component. Specifically, the collected environmental parameters may be temperature T, flotation odor concentration C, dust concentration D and humidity H. The monitoring results of the temperature sensors at each location can be expressed as: , in the ore dressing workshop 200 The gas sensor monitoring results at each location are expressed as: , in the ore dressing workshop 200 The monitoring results of the dust sensors at each location are expressed as follows: , in the ore dressing workshop 200 The monitoring results of humidity sensors at each location are expressed as: .

[0048] S2: Collect the start / stop status and operating frequency of each fan, as well as the opening degree of the skylight. The fan start and stop status F is expressed as , where 1 means on, 0 means off, and the fan operating frequency P is expressed as , unit is Hz. The ore dressing workshop 200 contains The skylight opening degree W is expressed as .in, The range is 0% (fully closed) to 100% (fully open).

[0049] S3: Preprocess the collected environmental parameters to obtain preprocessed environmental data.

[0050] S31: Determine outliers in environmental parameters using a Local Outlier Factor (LOF) algorithm. The Local Outlier Factor is a density-based anomaly detection method that identifies outliers by comparing the local density difference between a data point and its neighbors. The specific process of removing outliers can be as follows: S311: For each data point in the environmental parameter, calculate the k-distance of each data point. For each data point P, calculate the distance to its Kth environmental parameter nearest neighbor, called k-distance. The formula is as follows: Point o is the kth point closest to point p.

[0051] S312: Based on k-distance, calculate the reachability distance. For each data point to its neighbor point, the larger value of "k-neighbor distance of point o" and "direct distance between point p and o" is:

[0052] S313: Based on the reachable distance, calculate the local reachability density (LRD). For each data point p, calculate the average of the reachable distances of its neighboring points and take the inverse. The number of neighboring points is determined by k. in, is the set of k nearest neighbors of data point p S314: Based on the reachable density, calculate the local anomaly factor, which is the average value of the ratio of the local reachable density of the data point p to the local reachable densities of its k nearest neighbors.

[0053]

[0054] S315: Based on the local outlier factor, determine whether each data point is an outlier. Specifically, the larger the LOF value, the more likely the data point is an outlier. A threshold is set according to the LOF value, and points with values ​​higher than the threshold are considered outliers.

[0055] S32: Calculate the mean after removing outliers; S33: adding the mean value to the environmental parameter after removing the outliers to obtain environmental data; S34: normalize the environmental data. Exemplarily, the normalization process may adopt the following formula:

[0056] Among them, X min , X max It refers to a data set consisting of historical data of each environmental variable monitored by the environmental parameter detection component, and the maximum and minimum values ​​of each column of environmental variables after processing.

[0057] S35: synthesize the processed environmental parameters into a state vector to obtain pre-processed environmental data.

[0058] The state vector S is expressed as:

[0059] S4: input the obtained pre-processed environmental data into the intelligent fresh air control system, and calculate the control strategy through the intelligent fresh air control system; S41: inputting the obtained pre-processed environment data into the pre-trained proximal strategy optimization model; S42: The proximal strategy optimization model calculates the control strategy and generates control instructions for the fan and the skylight.

[0060] S5: Control the operation of the fan assembly 301 and the skylight assembly 302 according to the control strategy calculated by the intelligent fresh air control system.

[0061] S51: converting the control instructions of the fan and the skylight generated by the near-end strategy optimization model into actual control signals; S52: Control the opening or closing of the fan, the operating frequency of the fan and the opening of the skylight through the actual control signal.

[0062] According to the air control method of the mineral processing workshop 200 in the embodiment of the present application, local precise control of multi-source environmental parameters such as dust, temperature, humidity and odor concentration in the mineral processing workshop 200 can be achieved through intelligent algorithms, thereby solving occupational health hazards in production and alarms and production failures caused by local high temperatures of mechanical equipment in the mineral processing workshop 200.

[0063] Exemplarily, building a proximal policy optimization (PPO) model includes the following steps: (1) Network architecture design ① Input layer The dimension of the input layer is equal to the number of state variables, that is, .

[0064] ②Hidden layer Set up 4 fully connected hidden layers, each containing 128 neurons, and use the ReLU activation function.

[0065] ③Output layer According to the needs of the action space, the output layer is the parameters of the continuous action.

[0066] (2) Training process ① Collect experience Interact with the environment, record the state, action, reward and next state, and form an experience data set.

[0067] ②Calculate the advantage function Advantage Estimate: in, is the discount factor, is the GAE (generalized advantage estimate) parameter.

[0068] is the TD residual at time t, expressed as:

[0069] Among them, V(s) is the value network's estimate of the value of state s, is the reward obtained at time step t+1, is the discount factor.

[0070] ③ Update strategy, use the cut probability ratio strategy, limit the strategy update step size, and prevent over-update:

[0071] in, is the policy function, is the policy network parameter, is the cutting range, Indicated in Select action in status The probability distribution of .

[0072] Use gradient ascent method to update policy parameters :

[0073] ④Update the value network and calculate the mean square error loss: in, is the TD residual at time t, and N is the number of samples.

[0074] (3) Strategy selection After training, the PPO model learns the policy function , whose parameters It is obtained through the training optimization process, and the final strategy selection method is described as: in, is the policy function, S is the input state vector, and A is the output action vector. Policy function Based on the learned optimal strategy, the most appropriate control instruction A will be generated according to the evaluation of the current environmental state S. According to the generated control instruction A, the start and stop status of the fan, the operating frequency and the opening and closing degree of the skylight will be adjusted to optimize the environmental parameters in the mineral processing workshop 200 and ensure that they remain within the set ideal range.

[0075] Since the reward function is used to evaluate the quality of the actions taken by the agent in different states, it is used in the model's advantage function calculation and strategy update process, thereby guiding the optimization direction of the strategy.

[0076] Exemplarily, a reward function may be constructed, and the reward function design may include the following steps: (1) Reward function construction ①Set the ideal range of environmental parameters The ideal temperature range is ;The maximum allowable gas concentration is ; The ideal humidity range is ;The maximum allowable dust concentration is The ideal range of environmental parameters needs to be normalized in the same way. The ideal value of each parameter after normalization is , , , .

[0077] ② Reward function calculation Temperature Reward( ):

[0078] in, is the temperature reward weight.

[0079] Gas Concentration Rewards ( ):

[0080] in, is the gas concentration reward weight.

[0081] Humidity Bonus ( ):

[0082] in, is the moisture bonus weight.

[0083] Dust Concentration Reward ( ):

[0084] in, is the dust concentration reward weight.

[0085] Total reward function:

[0086] Combine the following Figure 4 The components of the electronic device 100 are described in detail: The processor 1031 is the control center of the electronic device 100, and may be a single processor 1031 or a collective term for multiple processing elements. For example, the processor 1031 is a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention, such as one or more DSPs, or one or more field programmable gate arrays (FPGAs).

[0087] In a specific implementation, as an embodiment, the processor 1031 may include one or more CPUs, such as Figure 4 0 and CPU1 shown in FIG. Moreover, as an embodiment, the electronic device 100 may include multiple processors 1031, each of which may be a single-core processor (Single-CPU) or a multi-core processor (Multi-CPU). The processor 1031 here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0088] The memory 1051 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 1051 may exist independently and be connected to the processor 1031 via the communication bus 1041. The memory 1051 may also be integrated with the processor 1031.

[0089] In a specific implementation, the memory 1051 is used to store the data of the present invention and execute the software program of the present invention. The processor 1031 can execute various functions of the electronic device 100 by running or executing the software program stored in the memory 1051 and calling the data stored in the memory 1051.

[0090] The electronic device 100 may further include a communication interface 1042 and a communication bus 1041 .

[0091] The communication interface 1042 uses any transceiver or other device to communicate with other devices or communication networks, such as a Radio Access Network (RAN), a Wireless Local Area Network (WLAN), etc. The communication interface 1042 may include a receiving unit to implement a receiving function, and a sending unit to implement a sending function.

[0092] The communication bus 1041 may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0093] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An air conditioning device for a mineral processing workshop, characterized in that: include: A fan assembly, the fan assembly comprising a plurality of fans, the fans being used to supply air from a first space area to a second space area; wherein the level of the first space area is lower than the level of the second space area; A skylight assembly, the skylight assembly comprising a plurality of skylights, the opening degree of the skylights being adjustable and used for communicating with the outside, and the horizontal height of the skylight assembly being higher than the second space area; An environmental parameter monitoring component, the environmental parameter monitoring component includes a plurality of air quality monitoring sensors, and the air quality monitoring sensors are used to monitor environmental parameters in the ore dressing workshop; An intelligent fresh air control system, wherein the intelligent fresh air control system is electrically connected to the skylight assembly, the fan assembly and the environmental parameter monitoring assembly, and the intelligent fresh air control system controls the operation of the skylight assembly and the fan assembly according to the environmental parameters monitored by the environmental parameter monitoring assembly.

2. The air conditioning device for a ore dressing workshop according to claim 1, characterized in that: The air quality monitoring sensor includes a dust concentration sensor, a temperature sensor, a flotation odor concentration sensor and a humidity sensor. The dust concentration sensor is used to monitor the dust concentration in the ore dressing workshop, the temperature sensor is used to monitor the temperature in the ore dressing workshop, the flotation odor concentration sensor is used to monitor the flotation odor concentration in the ore dressing workshop, and the humidity sensor is used to monitor the humidity in the ore dressing workshop.

3. An air control method for a mineral processing workshop, applied to the air control device for a mineral processing workshop according to claim 1 or 2, characterized in that: The air control method of the ore dressing workshop comprises: Collecting the environmental parameters in the ore dressing workshop through the environmental parameter monitoring component; Preprocessing the collected environmental parameters to obtain preprocessed environmental data; Inputting the obtained pre-processed environmental data into the intelligent fresh air control system, and calculating a control strategy through the intelligent fresh air control system; The operation of the fan assembly and the skylight assembly is controlled according to the control strategy calculated by the intelligent fresh air control system.

4. The air control method for a ore dressing workshop according to claim 3, characterized in that: The collected environmental parameters are preprocessed to obtain preprocessed environmental data including: Determining outliers in the environmental parameters by a local outlier factor algorithm; Calculate the mean after removing the outliers; The mean value is added to the environmental parameter after the outlier is removed to obtain environmental data; Normalizing the environmental data; The processed environmental parameters are synthesized into a state vector to obtain the pre-processed environmental data.

5. The air control method for a ore dressing workshop according to claim 4, characterized in that: Determining the outliers in the environmental parameters by the local outlier factor algorithm includes: For each data point in the environmental parameter, calculating the k-distance of each data point; Based on the k-distance, calculating the reachable distance; Based on the reachable distance, calculating the local reachable density; Based on the reachable density, calculating a local anomaly factor; Based on the local abnormality factor, it is determined whether each data point is an abnormal value.

6. The air control method for a ore dressing workshop according to claim 3, characterized in that: The air control method for a mineral processing workshop further includes: collecting the environmental parameters in the mineral processing workshop through the environmental parameter monitoring component, and at the same time collecting the start / stop status and operating frequency of each fan, as well as the opening degree of the skylight.

7. The air control method for a ore dressing workshop according to claim 3, characterized in that: The obtained pre-processed environmental data is input into the intelligent fresh air control system, and the control strategy calculated by the intelligent fresh air control system includes: Inputting the obtained pre-processed environment data into a pre-trained proximal strategy optimization model; The proximal strategy optimization model calculates the control strategy and generates control instructions for the fan and the skylight.

8. The air control method for a ore dressing workshop according to claim 7, characterized in that: The work of controlling the fan assembly and the skylight assembly according to the control strategy calculated by the intelligent fresh air control system also includes: Converting the control instructions of the fan and the skylight generated by the proximal strategy optimization model into actual control signals; The actual control signal is used to control the opening or closing of the fan, the operating frequency of the fan and the opening degree of the skylight.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor, the memory storing computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the air control method for a mineral processing workshop as described in any one of claims 3 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the air control method for a mineral processing workshop according to any one of claims 3 to 8.

Images