Artificial intelligence control system

Abstract

The invention discloses an artificial intelligence control system, and relates to the technical field of intelligent control, a selection module generates next-generation scheduling schemes by using a roulette selection method according to a fitness evaluation result of an initial scheduling scheme, and when the number of the generated next-generation scheduling schemes exceeds a number threshold value, the next-generation scheduling schemes are sent to a cross module; the cross module carries out cross operation on the next generation of scheduling scheme to generate a new scheduling scheme, the iteration module repeatedly carries out the operation steps of the selection module, the cross module and the variation module to carry out iteration operation, and when the number of times of iteration operation is equal to a number threshold value, a new generation of scheduling scheme is generated; the control system can automatically generate a scheduling scheme to control the operation of the dust suppression equipment based on the number of the dust suppression equipment supporting operation every day and the dust suppression requirement, the operation cost of the dust suppression equipment is reduced while the dust suppression effect is guaranteed, manual intervention is avoided, control is more accurate, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an artificial intelligence control system. Background Art

[0002] Atomizing humidification dust suppression equipment is a device used to control dust diffusion and increase air humidity during construction on site. These devices atomize water into tiny droplets and then release them into the air to form a layer of fine water mist, which effectively adsorbs and settles particulate matter suspended in the air to achieve the purpose of dust suppression. Atomizing humidification dust suppression equipment usually uses water as the atomizing medium, so it is harmless to the environment. Compared with traditional dust suppression methods such as spraying water and covering, atomizing humidification can reduce dust more efficiently and reduce pollution to the surrounding environment. Since construction sites usually have a certain area, several atomizing humidification dust suppression equipment are usually set up on the construction site, and several atomizing humidification dust suppression equipment are controlled and operated by a control system.

[0003] The prior art has the following deficiencies:

[0004] The existing control system of atomizing humidification dust suppression equipment is mainly operated manually. The operator directly controls the operation of the atomizing humidification dust suppression equipment through the control system according to the conditions of the construction site, or inputs a predetermined start time into the control system. When the predetermined start time is reached, the control system automatically controls the atomizing humidification dust suppression equipment to start operation. This manual intervention control method has the following defects:

[0005] 1. The control system has a low level of intelligence and cannot automatically generate the optimal scheduling plan based on the conditions of the construction site and the status of the atomizing humidification dust suppression equipment. Not only can the atomizing humidification dust suppression effect at the construction site not be guaranteed, but the atomizing humidification dust suppression equipment is easily over-activated, increasing dust suppression energy consumption;

[0006] 2. Manual intervention control is highly subjective and prone to misjudgment, resulting in over-activation or under-activation of the atomizing humidification dust suppression equipment. Second, manual control also requires corresponding operators, which increases labor costs. Summary of the invention

[0007] The purpose of the present invention is to provide an artificial intelligence control system to solve the deficiencies in the background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solutions: an artificial intelligence control system, comprising an initialization module, an evaluation module, a selection module, a crossover module, a mutation module, an iteration module, an output module and a control module;

[0009] Initialization module: obtains the number of dust suppression devices that support operation at the construction site and the total daily construction time, randomly generates the start time and end time for each dust suppression device, and generates several initial scheduling plans after adjusting the constraints through constraints;

[0010] Evaluation module: Use the fitness function to evaluate the fitness of each initial scheduling solution;

[0011] Selection module: Based on the fitness evaluation results of the initial scheduling scheme, the next-generation scheduling scheme is generated using the roulette wheel selection method. When the number of the next-generation scheduling schemes generated exceeds the quantity threshold, the next-generation scheduling scheme is sent to the cross-module;

[0012] Cross-module: performs cross-operation on the next generation scheduling scheme to generate a new scheduling scheme;

[0013] Mutation module: performs mutation operations on the new scheduling scheme to introduce randomness;

[0014] Iteration module: Repeat the operation steps of the selection module, crossover module, and mutation module for iterative operation. When the number of iterations is equal to the threshold, a new generation of scheduling scheme population is generated, and then the fitness function is used to analyze the new generation of scheduling scheme population to obtain the optimal scheduling scheme;

[0015] Output module: converts the optimal scheduling plan into control code;

[0016] Control module: Automatically controls the operation of dust suppression equipment at the construction site according to the control code.

[0017] In a preferred embodiment, the initialization module obtains information on the number of dust suppression devices supported for operation and the total daily construction duration from a configuration file of the construction site;

[0018] The start time and end time of each dust suppression device are randomly generated by generating a random number of minutes. The start time and end time of each dust suppression device are within the total daily construction time, and the start time and end time of the dust suppression devices do not overlap.

[0019] In a preferred embodiment, the initialization module obtains the number of dust suppression devices supported for operation from the configuration file of the construction site, including the following steps:

[0020] Obtain the atomizer atomization floating coefficient of the dust suppression equipment, the failure frequency of the control program, and the decibel level during operation;

[0021] The dust suppression coefficient yc is established by normalizing the atomizer atomization floating coefficient, the control program failure frequency, and the decibel level during operation. s ;

[0022] Dust suppression coefficient ycs The larger the value, the worse the state of the dust suppression equipment is, and the less support it can run. The dust suppression coefficient yc is obtained. s After the dust suppression coefficient yc s Value and preset operating threshold yx z Make a comparison;

[0023] If the dust suppression coefficient yc s Value ≥ operating threshold yx z , it is judged that the dust suppression equipment does not support operation, if the dust suppression coefficient yc s Value < operation threshold yx z , determine whether the dust suppression equipment supports operation.

[0024] In a preferred embodiment, the initialization module obtains the numbers of all dust suppression equipment in the construction site through the system log, and then obtains all historical dust suppression coefficients yc of the dust suppression equipment. s , all historical dust suppression coefficients yc s Establish a dust suppression coefficient set and obtain the dust suppression coefficient yc with the most recent date in the dust suppression coefficient set s value;

[0025] The average dust suppression coefficient of the dust suppression equipment is calculated based on the dust suppression coefficient set. The expression is: Where i = {1, 2, 3, ..., n}, n represents the dust suppression coefficient yc in the dust suppression coefficient set s The number of, and n is a positive integer, yc si Indicates the i-th dust suppression coefficient yc s Value, yc avg It represents the average value of dust suppression coefficient;

[0026] Then the operating threshold yx is set for each dust suppression device z Dynamic adjustment to obtain dynamic correction threshold yx 修正 , the calculation expression is: In the formula, yx 修正 is the dynamic correction threshold yx 修正 , yx z is the operating threshold, yc sz is the dust suppression coefficient value with the most recent date in the dust suppression coefficient set, yc avg represents the average value of dust suppression coefficient, i = {1, 2, 3, ..., n}, n represents the dust suppression coefficient yc in the dust suppression coefficient set s The number of, and n is a positive integer, yc si Indicates the i-th dust suppression coefficient yc s value;

[0027] When judging the operating status of all dust suppression equipment on that day, each dust suppression equipment will generate a dynamic correction threshold value yx 修正, obtain the dust suppression coefficient yc of the dust suppression equipment on that day s After the dust suppression coefficient yc of the dust suppression equipment is s Value and dynamic correction threshold yx 修正 Compare and determine whether the dust suppression equipment supports operation.

[0028] In a preferred embodiment, the iteration module regenerates a new generation of scheduling solution population, and then analyzes the new generation of scheduling solution population through the fitness function to obtain the optimal scheduling solution, and then sends the optimal scheduling solution to the output module, including the following steps:

[0029] The iteration module repeats the operation steps of the selection module, the crossover module, and the mutation module to perform iterative operations. When the number of iteration operations is equal to the number threshold, a new generation of scheduling scheme population is generated;

[0030] Calculate and obtain the fitness of all new generation scheduling schemes in the new generation scheduling scheme population, and sort all new generation scheduling schemes from large to small according to fitness to generate a scheme sorting table;

[0031] The new generation scheduling scheme ranked first in the scheme ranking table is taken as the optimal scheduling scheme.

[0032] In a preferred embodiment, the output module converts the optimal scheduling scheme into a control code comprising the following steps:

[0033] Obtain the optimal scheduling plan from the iteration module. The optimal scheduling plan includes the working time period of each device;

[0034] Convert the extracted scheduling information into a code format executed by the control module, including converting time information and device identification into corresponding control commands;

[0035] Generate control codes according to the converted format, including equipment start, stop, and adjustment of working time;

[0036] The control module automatically controls the operation of the dust suppression equipment at the construction site according to the control code, comprising the following steps:

[0037] The device identification, start time and stop time are received through the device control function, and the device operation is controlled.

[0038] In a preferred embodiment, the selection module generates a next generation scheduling solution, and when the number of the generated next generation scheduling solutions exceeds the number threshold, sending the next generation scheduling solution to the cross module includes the following steps:

[0039] After obtaining the fitness of all initial scheduling solutions, calculate the fitness ratio ΔS of each initial scheduling solution, the expression is: ΔS = g s / z s, where g s is the fitness of the initial scheduling solution, z s is the total fitness;

[0040] Use the roulette wheel selection method to select the initial scheduling plan according to the fitness ratio;

[0041] Generate a random number using a random number generator Assume that the fitness ratios of all initial scheduling schemes are ΔS1, ΔS2, ΔS3, ..., ΔS n , n is the number of initial scheduling solutions, and n is a positive integer;

[0042] The fitness ratio cumulative probability of the first initial scheduling scheme is FL1 = ΔS1, the fitness ratio cumulative probability of the second initial scheduling scheme is FL2 = ΔS1 + ΔS2, and the fitness ratio cumulative probability of the nth initial scheduling scheme is FL2 = ΔS1 + ΔS2 + ΔS3 + ... + ΔS n ;

[0043] Set the first fitness ratio cumulative probability ≥ random number The initial scheduling scheme is used as the next generation scheduling scheme.

[0044] In a preferred embodiment, the calculation expression of the fitness function is: In the formula, g s is the fitness of the initial scheduling scheme, CD is the dust concentration at the construction site when the initial scheduling scheme is used, ω1 is the weight of the dust concentration at the construction site when the initial scheduling scheme is used, NH is the energy consumption when the initial scheduling scheme is used, ω2 is the energy consumption weight when the initial scheduling scheme is used, and ω1>ω2>0.

[0045] In a preferred embodiment, the crossover module performs crossover operation on the next generation scheduling scheme to generate a new scheduling scheme, including the following steps:

[0046] Determine the time point of the crossover operation, from which the information of the two next generation scheduling schemes will be crossed;

[0047] The information of two next-generation scheduling schemes is cut at the intersection point by single-point crossover, and cross-combined to obtain a new scheduling scheme;

[0048] Repeat the above steps until the new scheduling scheme reaches the predetermined number and then stop the crossover operation.

[0049] In a preferred embodiment, the mutation module performs a mutation operation on the new scheduling scheme to introduce randomness, including the following steps:

[0050] Determine the time point of the mutation operation and mutate the new scheduling plan near this time point;

[0051] Perform mutation operations on the new scheduling plan information near the time point;

[0052] The new scheduling scheme is mutated to generate a new generation of scheduling scheme;

[0053] Repeat the above steps until the number of new generation scheduling solutions reaches the predetermined number and then stop the mutation operation.

[0054] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0055] 1. The present invention obtains the number of dust suppression equipment supported and the total daily construction time of the construction site through the initialization module, randomly generates the start time and the end time for each dust suppression equipment, and generates several initial scheduling schemes after adjusting the constraints through constraints. The selection module generates the next generation scheduling scheme by using the roulette selection method according to the fitness evaluation results of the initial scheduling scheme. When the number of the next generation scheduling schemes generated exceeds the number threshold, the next generation scheduling scheme is sent to the cross module. The cross module crosses the next generation scheduling scheme to generate a new scheduling scheme. The iteration module repeats the operation steps of the selection module, the cross module, and the mutation module to perform iterative operations. When the number of iterative operations is equal to the number threshold, a new generation scheduling scheme is generated. The control system can automatically generate a scheduling scheme based on the number of dust suppression equipment supported and the dust suppression demand to control the operation of the dust suppression equipment, thereby ensuring the dust suppression effect and reducing the operating cost of the dust suppression equipment. Moreover, there is no manual intervention, the control is more accurate and the labor cost is eliminated.

[0056] 2. The present invention establishes the dust suppression coefficient yc by normalizing the atomizer atomization floating coefficient, the control program failure frequency and the decibel level during operation. s , dust suppression coefficient yc s The larger the value, the worse the state of the dust suppression equipment is, and the less it can be operated. s Value and preset operating threshold yx z The comparison results can be used to determine whether the dust suppression equipment can still be operated. The comprehensive analysis of multiple parameters can not only provide a more comprehensive analysis and improve the data processing efficiency, but also determine whether the dust suppression equipment can still be operated. The dust suppression equipment that does not support operation can be selected from the scheduling plan, further ensuring the dust suppression effect of the construction site;

[0057] 3. When the present invention determines the operating status of all dust suppression equipment on the day, each dust suppression equipment will generate a dynamic correction threshold value yx 修正 , obtain the dust suppression coefficient yc of the dust suppression equipment on that day s After the dust suppression coefficient yc of the dust suppression equipment iss Value and dynamic correction threshold yx 修正 By making a comparison, different dust suppression equipment can be evaluated with different evaluation standards, effectively improving the evaluation accuracy of dust suppression equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0059] Figure 1 The present invention is a flow chart of the method.

[0060] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Example 1: Please refer to Figure 1 As shown, the artificial intelligence control system described in this embodiment includes an initialization module, an evaluation module, a selection module, a crossover module, a mutation module, an iteration module, an output module and a control module;

[0063] Initialization module: obtain the number of dust suppression devices that support operation and the total daily construction time of the construction site, randomly generate the start time and end time for each dust suppression device, and generate several initial scheduling plans after constraint adjustment. The constraint adjustment is to ensure that the start time and end time of the dust suppression devices do not overlap, to ensure that only one device works at the same time, and the start time and end time are guaranteed to be within the total daily construction time. Send several initial scheduling plans to the evaluation module;

[0064] Evaluation module: Use the fitness function to evaluate the fitness of each initial scheduling solution, and send the evaluation results to the selection module, specifically:

[0065] The calculation expression of the fitness function is: In the formula, g sis the fitness of the initial scheduling scheme, CD is the dust concentration of the construction site when the initial scheduling scheme is used, ω1 is the weight of the dust concentration of the construction site when the initial scheduling scheme is used, NH is the energy consumption when the initial scheduling scheme is used, ω2 is the energy consumption weight when the initial scheduling scheme is used, and ω1>ω2>0;

[0066] Specifically: The goal of the fitness function is to find a scheduling plan that can effectively reduce the dust concentration and save the energy consumption of equipment. The larger the fitness value of the initial scheduling plan, the more comprehensive the initial scheduling plan is (effectively reducing the dust concentration in the construction site while reducing energy consumption).

[0067] Selection module: Based on the fitness evaluation results of the initial scheduling scheme, the roulette wheel selection method is used to generate the next generation scheduling scheme. When the number of the next generation scheduling schemes generated exceeds the quantity threshold, the next generation scheduling scheme is sent to the cross module to select the initial scheduling scheme with high fitness to increase the probability of the initial scheduling scheme with high fitness in the next generation. Specifically:

[0068] After obtaining the fitness of all initial scheduling solutions, calculate the fitness ratio ΔS of each initial scheduling solution, the expression is: ΔS = g s / z s , where g s is the fitness of the initial scheduling solution, z s The total fitness is the sum of the fitness of all initial scheduling schemes. The roulette wheel selection method is used to select the initial scheduling scheme according to the size of the fitness ratio. The initial scheduling scheme with a large fitness ratio is given priority. A random number is generated through a random number generator. Then, the initial scheduling scheme is selected according to the ratio of the roulette wheel. Suppose the fitness ratios of all initial scheduling schemes are ΔS1, ΔS2, ΔS3, ..., ΔS n , n is the number of initial scheduling schemes, and n is a positive integer, then the fitness proportional cumulative probability FL1 of the first initial scheduling scheme is ΔS1, the fitness proportional cumulative probability FL2 of the second initial scheduling scheme is ΔS1+ΔS2, and the fitness proportional cumulative probability FL2 of the nth initial scheduling scheme is ΔS1+ΔS2+ΔS3+...+ΔS n , the first fitness ratio cumulative probability ≥ random number The initial scheduling scheme is used as the next generation scheduling scheme;

[0069] To better illustrate the above solution, we give the following example:

[0070] Assume that there are 5 initial scheduling schemes, and the fitness ratios of the 5 initial scheduling schemes are ΔS1=0.208, ΔS2=0.156, ΔS3=0.234, ΔS4=0.182, and ΔS5=0.220 respectively; then the cumulative probabilities of the fitness ratios of the 5 initial scheduling schemes are: FL1=0.208, FL2=0.364, FL3=0.598, FL4=0.780, and FL5=1.000;

[0071] If the random number generated by the random number generator Since FL4=0.780> Therefore, the fourth initial scheduling scheme is selected as the next generation scheduling scheme;

[0072] If the random number generated by the second round of random number generator Because Therefore, the fifth initial scheduling scheme is selected as the next generation scheduling scheme;

[0073] If the third round of random number generator generates random numbers Because Therefore, the second initial scheduling scheme is selected as the next generation scheduling scheme;

[0074] If the quantity threshold is set to 3, the 4th initial scheduling plan, the 5th initial scheduling plan and the 2nd initial scheduling plan are used as the next generation scheduling plan. The selection process is based on random numbers and fitness ratios, so that individuals with higher fitness have a greater probability of being selected, but at the same time a certain degree of randomness is introduced to ensure that the algorithm can better explore the search space;

[0075] Crossover module: performs crossover operations on the next generation scheduling scheme to generate a new scheduling scheme, which is sent to the mutation module. Specifically:

[0076] Determine the point or position of the crossover operation. This point can be a time point, indicating that from this time point on, the information of the two next-generation scheduling plans will be crossed. The information of the two next-generation scheduling plans is cut at the intersection point by a single-point crossover method, and a new scheduling plan is obtained by cross-combination. Repeat the above steps to generate a sufficient number of new scheduling plans until the new scheduling plans reach a predetermined number and the crossover operation is stopped;

[0077] To better illustrate the above solution, we give the following example:

[0078] Assuming that the intersection point is time point t, the next generation scheduling scheme A and the next generation scheduling scheme B are as follows:

[0079] Next generation scheduling scheme A: Device A (3:00-5:30), Device B (8:15-12:45), Device C (15:30-18:30)

[0080] Next generation scheduling scheme B: device A (2:30-6:00), device B (7:00-10:30), device C (14:00-18:00);

[0081] Take the part after the intersection point t for intersection, as follows:

[0082] The new scheduling plan generated is: device A (3:00-5:30), device B (7:00-10:30), device C (14:00-18:00).

[0083] Mutation module: mutates the new scheduling scheme and introduces some randomness, specifically:

[0084] Determine the time point of mutation operation, which means to mutate the new scheduling plan near this time point, and perform a small mutation operation on the new scheduling plan information near the mutation point. The mutation can be some random, small-scale changes, such as adjusting the working time of a certain device or exchanging the working time of two devices. After the new scheduling plan is mutated, a new generation of scheduling plan is generated. Repeat the above steps to mutate a sufficient number of new scheduling plans until the number of new generation scheduling plans reaches a predetermined number and then stop the mutation operation;

[0085] Assume that the first new scheduling scheme is selected for mutation operation, and the mutation time point is selected in the working time period of device B. The mutation can be to delay or advance the working time of device B by a certain time, or randomly select a new time period to replace the original time, for example:

[0086] New scheduling plan: Equipment A (3:00-5:30), Equipment B (8:15-12:45), Equipment C (15:30-18:30);

[0087] New generation scheduling scheme: equipment A (3:00-5:30), equipment B (8:15-12:45+δ), equipment C (15:30-18:30);

[0088] Among them, δ represents a small random change. Through the mutation operation, we introduce a small random change, which may make the individual closer to some unexplored solutions, thus facilitating the global search.

[0089] More specific:

[0090] Suppose we have a scheduling plan that includes the working hours of three devices, and the mutation point is selected in the working time period of device B. The mutation can be to adjust the working time of device B or to exchange the working times of two devices;

[0091] Assume that the new scheduling plan is: device A (3:00-5:30), device B (8:15-12:45), device C (15:30-18:30);

[0092] Mutation operation 1: Adjust the working time of device B. Make a small adjustment during the working time of device B, such as delaying its working time by 30 minutes:

[0093] The new generation scheduling scheme is: equipment A (3:00-5:30), equipment B (8:15-13:15), equipment C (15:30-18:30);

[0094] Mutation operation 2: Exchange the working time of the two devices. Select a time point in the working time period of device B and exchange the working time of device B and device C:

[0095] The new generation scheduling plan is: equipment A (3:00-5:30), equipment B (15:30-18:30), equipment C (8:15-13:15).

[0096] Iteration module: Repeat the operation steps of the selection module, crossover module, and mutation module for iterative operation. When the number of iterations is equal to the number threshold, a new generation of scheduling scheme population is generated. After the fitness function is used to analyze the new generation of scheduling scheme population to obtain the optimal scheduling scheme, the optimal scheduling scheme is sent to the output module. Specifically:

[0097] The iteration module repeats the operation steps of the selection module, the crossover module, and the mutation module to perform iterative operations. When the number of iteration operations is equal to the number threshold, a new generation of scheduling scheme population is generated;

[0098] Calculate and obtain the fitness of all new generation scheduling schemes in the new generation scheduling scheme population, and sort all new generation scheduling schemes from large to small according to fitness to generate a scheme sorting table;

[0099] The new generation scheduling scheme ranked first in the scheme ranking table is taken as the optimal scheduling scheme.

[0100] Output module: After converting the optimal scheduling plan into control code, the control code is sent to the control module, specifically:

[0101] The optimal scheduling solution obtained from the iteration module usually includes the working time period of each device. This information is extracted so as to be converted into control code. The extracted scheduling information is converted into a code format that can be executed by the device control system. This may involve converting time information, device identification, etc. into corresponding control commands, and generating control codes according to the converted format. This may include relevant instructions such as device start, stop, and adjust working hours.

[0102] Control module: Automatically controls the operation of dust suppression equipment at the construction site according to the control code, specifically:

[0103] First, we need to define a device control function, which receives the device identification, start time and stop time, and controls the operation of the device based on this information. In this example, we used a simple control_device function, which contains the logic of simulating device control. In the control_device function, we simulated the code of actual device control. In the actual scenario, this will involve communication with the device control system, sending control instructions, etc. The following is an example of simulating the Modbus protocol, which includes device address mapping and corresponding Modbus write commands. Define the main function of the control module, control_system, which is responsible for traversing the optimal scheduling plan and calling the device control function in turn to control the operation of each device. Finally, call the main function of the control module, pass the optimal scheduling plan to the control module, and realize the automatic operation of the dust suppression equipment on the construction site.

[0104] See also Figure 2 As shown, the present application obtains the number of dust suppression equipment supported for operation and the total daily construction time of the construction site through the initialization module, randomly generates the start time and end time for each dust suppression equipment, and generates several initial scheduling schemes after adjusting the constraints through constraints. The selection module generates the next generation scheduling scheme based on the fitness evaluation results of the initial scheduling scheme using the roulette selection method. When the number of the generated next generation scheduling schemes exceeds the quantity threshold, the next generation scheduling scheme is sent to the cross module. The cross module crosses the next generation scheduling scheme to generate a new scheduling scheme. The iteration module repeats the operation steps of the selection module, the cross module, and the mutation module to perform iterative operations. When the number of iterative operations is equal to the number threshold, a new generation scheduling scheme is generated. The control system can automatically generate a scheduling scheme based on the number of dust suppression equipment supported for operation and the dust suppression demand to control the operation of the dust suppression equipment, thereby ensuring the dust suppression effect while reducing the operating cost of the dust suppression equipment. Moreover, there is no human intervention, the control is more accurate and the labor cost is eliminated.

[0105] Embodiment 2: The initialization module obtains the number of dust suppression devices that support operation and the total daily construction time of the construction site, randomly generates a start time and an end time for each dust suppression device, and generates several initial scheduling schemes after constraint adjustment. The constraint adjustment is to ensure that the start time and the end time between the dust suppression devices do not overlap, so as to ensure that only one device works at the same time, and the start time and the end time are guaranteed to be within the total daily construction time, including the following steps:

[0106] First, obtain the information of the number of dust suppression devices supported and the total daily construction time from the configuration file of the construction site, and randomly generate the start time and end time of each dust suppression device to ensure that it is within the total daily construction time. This can be achieved by generating random minutes and converting them into time format to ensure that the generated initial scheduling plan meets the constraints, that is, the start time and end time of the dust suppression devices do not overlap;

[0107] The start and end times of each dust suppression device are randomly generated by generating random minutes to ensure that the following steps are included within the total daily construction time:

[0108] Set basic information: determine the total daily construction time and the number of dust suppression equipment. For example, assume the total daily construction time is 10 hours and there are 3 dust suppression equipment;

[0109] Generate random minutes: Generate random minutes for each dust suppression device. This can be achieved by randomly selecting from the range of 0 to the total daily working time, which means that the working time of each device will be randomly distributed throughout the working hours of the day.

[0110] Convert to time format: Convert the generated random minutes to time format, which includes converting the minutes into hours and minutes, and ensuring that it is within a reasonable time range, such as between 0:00 and 23:59;

[0111] Generate a schedule: For each dust suppression device, create a schedule using the generated random start and end times, which will form an initial list of random schedules;

[0112] Check constraints: Check the generated initial scheduling plan to ensure that no equipment works in the same time period, and the start time and end time are within the total daily construction time. If a conflict is found, the random minutes can be adjusted or regenerated to meet the constraints.

[0113] Obtaining the number of dust suppression devices supported for operation from the construction site configuration file includes the following steps:

[0114] Obtain the atomizer atomization floating coefficient, the control program failure frequency and the decibel level during operation;

[0115] The calculation expression of the atomizer atomization floating coefficient is: H(t) is the real-time atomization degree of the atomizer, [t x , t y ] is the period of liquid pressure warning, [t i , t j ] is the period of nozzle damage warning. The larger the atomization floating coefficient of the atomizer, the worse the atomization effect of the dust suppression equipment atomizer is, and the less supportive it is for use;

[0116] Generally speaking, the liquid pressure of the atomizer needs to be kept within a pressure range. When the liquid pressure is too high or too low, it will affect the atomization degree. When the liquid pressure is too high, it will not only increase the waste of water resources, but also may cause damage to the atomizer nozzle. When the liquid pressure is too low, it will directly lead to a decrease in atomization degree and fail to achieve the ideal atomization state. Therefore, the period when the liquid pressure is not within the pressure range is the period of liquid pressure warning;

[0117] If the liquid pressure is too high or too low, it will affect the atomization degree, which is manifested as follows:

[0118] Excessive liquid pressure:

[0119] Over-refinement: When the liquid pressure is too high, the sprayed liquid may be over-refinement, forming very small droplets, which may lead to increased atomization and produce an over-fine atomization effect;

[0120] Unstable spray direction: Excessive liquid pressure may cause the liquid spray direction of the atomizing nozzle to be unstable, making it difficult for the droplets to be evenly distributed in the target area;

[0121] Liquid pressure is too low:

[0122] Large droplets: When the liquid pressure is too low, the sprayed liquid droplets may be relatively large and not fine enough, which may lead to reduced atomization and larger droplets;

[0123] Poor uniformity: Too low liquid pressure may result in poor uniformity of droplets, making the atomization effect less uniform and complete than expected;

[0124] When there is a slight damage on the nozzle, it has little effect on the overall atomization effect of the atomizer. However, when the damage on the nozzle becomes larger and larger, the atomization effect will deteriorate or even fail to atomize. Therefore, the period when the damage degree of the nozzle exceeds the damage threshold is the period of nozzle damage warning.

[0125] When the nozzle is damaged more and more, the atomization effect will become worse or even unable to atomize, specifically:

[0126] Uneven droplets: A damaged nozzle may cause the liquid to be unevenly affected during the spraying process, making the droplet size and distribution inconsistent, which will lead to uneven atomization effect, and some areas may have too much or too little atomization;

[0127] Droplets are too large or too small: A damaged nozzle may change the speed or mode of liquid outflow, making the droplets too large or too small. The abnormal droplet size may make the atomization effect not meet expectations;

[0128] Deviation of spray direction: Damage to the nozzle may cause the spray direction of the liquid to deviate, making the atomization coverage not meet the requirements and causing uneven atomization effect;

[0129] Liquid leakage: A damaged nozzle may cause liquid to leak out when not spraying, which will not only lead to uneven atomization effect, but also cause waste of resources;

[0130] Reduced atomization efficiency: A damaged nozzle will affect the atomization efficiency of the liquid, making it impossible to effectively atomize a large amount of liquid into fine droplets, reducing the atomization effect;

[0131] Difficult maintenance: A damaged nozzle may make equipment maintenance more difficult, requiring more frequent maintenance and nozzle replacement.

[0132] The fault frequency of the control program is obtained as follows:

[0133] Connect the dust suppression equipment to the monitoring system. This can be achieved by connecting the equipment to sensors, PLCs (programmable logic controllers) or other monitoring devices. Configure the data acquisition system to ensure that it can capture key parameters and status information related to the dust suppression equipment control program. This may include data related to equipment operation, sensor readings, control commands, etc. Set up a real-time monitoring system to be able to monitor the operating status of the dust suppression equipment in real time. This can be done through real-time monitoring tools such as SCADA (supervisory control and data acquisition system). Then the control program failure frequency = control program failure times / dust suppression equipment trial operation time;

[0134] The greater the control program failure frequency, the more control program failures there are during the trial operation of the dust suppression equipment. When the control program fails, it may cause the dust suppression equipment to start abnormally (for example, it cannot maintain a stable atomization effect). Specifically:

[0135] Startup failure: Frequent failures in the control program may cause the dust suppression equipment to encounter problems during the startup process, making the equipment unable to start normally. This may be caused by incorrect or lost control signals during the startup process;

[0136] Unstable operation: Failures in the control program may cause the dust suppression equipment to become unstable during operation, which may manifest as erratic stopping and starting of the equipment during operation, as well as performance fluctuations;

[0137] Incorrect operation: A control program failure may cause the device to perform an incorrect operation or command, which may include incorrect device configuration, misinterpreted sensor data, etc., causing the device to perform incorrect actions;

[0138] Safety risks: Frequent failures in control procedures may increase the safety risks of dust suppression equipment. For example, control failures during the start-up or stop process may cause unexpected movement of equipment parts, increasing the safety risks of operators and the equipment itself.

[0139] Equipment damage: Failure of the control program may cause the components of the dust suppression equipment to be improperly operated, resulting in damage to the equipment. For example, frequent start and stop processes may accelerate the wear of equipment parts.

[0140] The steps to obtain the decibel level at runtime are as follows:

[0141] Install noise sensors at appropriate locations around the dust suppression equipment. These sensors can be dedicated noise sensors or multifunctional sensors equipped with noise measurement capabilities. Ensure that the noise sensors are located in locations that represent the entire dust suppression equipment operating area. Multiple sensors may be required to cover different areas, especially when the equipment has multiple operating parts or there are noise sources around the equipment. Connect the noise sensors to the monitoring system or data acquisition system. This can be done through wired or wireless connections, depending on the characteristics of the equipment and sensors. Configure the noise sensors in the monitoring system and ensure that their settings match the measurement requirements. This may include setting parameters such as measurement range and sampling frequency. Start the dust suppression equipment and monitor the noise sensor readings in real time. The monitoring system should be able to provide real-time readings of noise levels in decibels (dB);

[0142] The higher the decibel level during operation, the more likely the dust suppression device has the following anomalies that make it unusable:

[0143] Mechanical failure: Abnormal decibel levels may be caused by mechanical failures within the dust suppression equipment, which may include bearing problems, drive train failures, fan imbalance, etc.

[0144] Fan problems: Increased decibel levels may indicate a problem with the fan or blower, such as damaged blades, imbalance, or worn bearings, which can cause unusual noise levels;

[0145] Liquid flow problems: Abnormal or unstable liquid flow in the dust suppression equipment may cause increased noise, which may be related to pipe blockage, pump problems or other liquid flow anomalies;

[0146] Shock and vibration: Abnormal decibel levels may be caused by vibration or vibration of the equipment, which may be caused by improper installation of the equipment, unstable foundation, or malfunctioning vibrating components;

[0147] Air duct blockage: Blockage in the air duct may result in obstruction of air flow, which may cause an increase in noise levels. This may be caused by dust accumulation, debris or other obstructions;

[0148] Poor operating conditions: High noise levels may be caused by the equipment operating in poor environmental conditions. For example, excessive temperature, excessive friction or a harsh working environment can all lead to abnormal noise levels.

[0149] Specifically, the atomizer atomization floating coefficient, the control program failure frequency, and the decibel level during operation are obtained during a trial run before the dust suppression equipment is normally put into use.

[0150] The dust suppression coefficient yc is established by normalizing the atomizer atomization floating coefficient, the control program failure frequency, and the decibel level during operation. s , the expression is: Where, wh f is the atomizer atomization floating coefficient, cb is the fault frequency of the control program, fb is the decibel level during operation, α, β, γ are the proportional coefficients of the atomizer atomization floating coefficient, the fault frequency of the control program and the decibel level during operation, and α, β, γ are all greater than 0;

[0151] Dust suppression coefficient yc s The larger the value, the worse the state of the dust suppression equipment itself is, and the less it supports operation. Therefore, the dust suppression coefficient yc is obtained. s After the dust suppression coefficient yc s Value and preset operating threshold yx z For comparison, if the dust suppression coefficient yc s Value ≥ operating threshold yx z , it is judged that the dust suppression equipment does not support operation, if the dust suppression coefficient yc s Value < operation threshold yx z , determine whether the dust suppression equipment supports operation;

[0152] If the status of the dust suppression equipment is not checked before the dust suppression equipment scheduling plan is completed at the construction site, the dust suppression equipment may fail during the construction process and become unusable. At this time, it will take a certain amount of time for the control system to generate a new scheduling plan, which may cause problems such as construction suspension during this period.

[0153] Therefore, the present application establishes the dust suppression coefficient yc by normalizing the atomizer atomization floating coefficient, the control program failure frequency, and the decibel level during operation. s , dust suppression coefficient yc s The larger the value, the worse the state of the dust suppression equipment is, and the less it can be operated. s Value and preset operating threshold yx z The comparison results are used to determine whether the dust suppression equipment can still support operation. The comprehensive analysis of multiple parameters not only makes the analysis more comprehensive and improves data processing efficiency, but also determines whether the dust suppression equipment can still support operation. Dust suppression equipment that does not support operation can be selected from the scheduling plan, further ensuring the dust suppression effect of the construction site.

[0154] Embodiment 3: In the above embodiment 2, a unified evaluation standard method is adopted for all dust suppression equipment in the construction site. However, for some construction sites with a large area, several dust suppression equipment will be set up during actual use. Since the positions of the dust suppression equipment are different and the construction environments are different, the use status of the several dust suppression equipment will be different. If the same evaluation standard method is adopted, the evaluation may be inaccurate, which is not convenient for the maintenance and management of the dust suppression equipment.

[0155] Based on this, this embodiment proposes a dynamic evaluation index that can set the operating threshold value yx for different dust suppression equipment. z Dynamic adjustment can improve the accuracy of dust suppression equipment assessment. The specific plan is as follows:

[0156] The initialization module obtains the numbers of all dust suppression equipment at the construction site through the system log, and then obtains all historical dust suppression coefficients yc of the dust suppression equipment. s , all historical dust suppression coefficients yc s Establish a dust suppression coefficient set and obtain the dust suppression coefficient yc with the most recent date in the dust suppression coefficient set s value;

[0157] The average dust suppression coefficient of the dust suppression equipment is calculated based on the dust suppression coefficient set. The expression is: Where i = {1, 2, 3, ..., n}, n represents the dust suppression coefficient yc in the dust suppression coefficient set s The number of, and n is a positive integer, yc si Indicates the i-th dust suppression coefficient yc s Value, yc avg It represents the average value of dust suppression coefficient;

[0158] Then the operating threshold yx is set for each dust suppression device z Dynamic adjustment to obtain dynamic correction threshold yx 修正 , the calculation expression is: In the formula, yx修正 is the dynamic correction threshold yx 修正 , yx z is the operating threshold, yc sz is the dust suppression coefficient value with the most recent date in the dust suppression coefficient set, yc avg represents the average value of dust suppression coefficient, i = {1, 2, 3, ..., n}, n represents the dust suppression coefficient yc in the dust suppression coefficient set s The number of, and n is a positive integer, yc si Indicates the i-th dust suppression coefficient yc s value.

[0159] In this way, when judging the operating status of all dust suppression equipment on that day, each dust suppression equipment will generate a dynamic correction threshold value yx 修正 , obtain the dust suppression coefficient yc of the dust suppression equipment on that day s After the dust suppression coefficient yc of the dust suppression equipment is s Value and dynamic correction threshold yx 修正 By making a comparison, different dust suppression equipment can be evaluated with different evaluation standards, effectively improving the evaluation accuracy of dust suppression equipment.

[0160] Specifically, the dust suppression coefficient set does not include the dust suppression coefficient obtained on the day.

[0161] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0162] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0163] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0164] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0165] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of a variation operation or replacement within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An artificial intelligence control system, characterized in that: It includes an initialization module, an evaluation module, a selection module, a crossover module, a mutation module, an iteration module, an output module and a control module; Initialization module: obtains the number of dust suppression devices that support operation at the construction site and the total daily construction time, randomly generates the start time and end time for each dust suppression device, and generates several initial scheduling plans after adjusting the constraints through constraints; Evaluation module: Use the fitness function to evaluate the fitness of each initial scheduling solution; Selection module: Based on the fitness evaluation results of the initial scheduling scheme, the next-generation scheduling scheme is generated using the roulette wheel selection method. When the number of the next-generation scheduling schemes generated exceeds the quantity threshold, the next-generation scheduling scheme is sent to the cross-module; Cross-module: performs cross-operation on the next generation scheduling scheme to generate a new scheduling scheme; Mutation module: performs mutation operations on the new scheduling scheme to introduce randomness; Iteration module: Repeat the operation steps of the selection module, crossover module, and mutation module for iterative operation. When the number of iterations is equal to the threshold, a new generation of scheduling scheme population is generated, and then the fitness function is used to analyze the new generation of scheduling scheme population to obtain the optimal scheduling scheme; Output module: converts the optimal scheduling plan into control code; Control module: Automatically controls the operation of dust suppression equipment at the construction site according to the control code.

2. An artificial intelligence control system according to claim 1, characterized in that: The initialization module obtains information about the number of dust suppression devices supported and the total daily construction time from the configuration file of the construction site; The start time and end time of each dust suppression device are randomly generated by generating a random number of minutes. The start time and end time of each dust suppression device are within the total daily construction time, and the start time and end time of the dust suppression devices do not overlap.

3. An artificial intelligence control system according to claim 2, characterized in that: The initialization module obtains the number of dust suppression devices supported for operation from the configuration file of the construction site, including the following steps: Obtain the atomizer atomization floating coefficient of the dust suppression equipment, the failure frequency of the control program, and the decibel level during operation; The dust suppression coefficient yc is established by normalizing the atomizer atomization floating coefficient, the control program failure frequency, and the decibel level during operation. s ; Dust suppression coefficient yc s The larger the value, the worse the state of the dust suppression equipment is, and the less support it can run. The dust suppression coefficient yc is obtained. s After the dust suppression coefficient yc s Value and preset operating threshold yx z Make a comparison; If the dust suppression coefficient yc s Value ≥ operating threshold yx z , it is judged that the dust suppression equipment does not support operation, if the dust suppression coefficient yc s Value < operation threshold yx z , determine whether the dust suppression equipment supports operation.

4. An artificial intelligence control system according to claim 3, characterized in that: The initialization module obtains the numbers of all dust suppression equipment at the construction site through the system log, and then obtains all historical dust suppression coefficients yc of the dust suppression equipment. s , all historical dust suppression coefficients yc s Establish a dust suppression coefficient set and obtain the dust suppression coefficient yc with the most recent date in the dust suppression coefficient set s value; The average dust suppression coefficient of the dust suppression equipment is calculated based on the dust suppression coefficient set. The expression is: Where i = {1, 2, 3, ..., n}, n represents the dust suppression coefficient yc in the dust suppression coefficient set s The number of, and n is a positive integer, yc si Indicates the i-th dust suppression coefficient yc s Value, yc avg It represents the average value of dust suppression coefficient; Then the operating threshold yx is set for each dust suppression device z Dynamic adjustment to obtain dynamic correction threshold yx 修正 , the calculation expression is: In the formula, yx 修正 is the dynamic correction threshold yx 修正 , yx z is the operating threshold, yc sz is the dust suppression coefficient value with the most recent date in the dust suppression coefficient set, yc avg represents the average value of dust suppression coefficient, i = {1, 2, 3, ..., n}, n represents the dust suppression coefficient yc in the dust suppression coefficient set s The number of, and n is a positive integer, yc si Indicates the i-th dust suppression coefficient yc s value; When judging the operating status of all dust suppression equipment on that day, each dust suppression equipment will generate a dynamic correction threshold value yx 修正 , obtain the dust suppression coefficient yc of the dust suppression equipment on that day s After the dust suppression coefficient yc of the dust suppression equipment is s Value and dynamic correction threshold yx 修正 Compare and determine whether the dust suppression equipment supports operation.

5. An artificial intelligence control system according to claim 4, characterized in that: The iteration module regenerates a new generation of scheduling solution population, and then analyzes the new generation of scheduling solution population through the fitness function to obtain the optimal scheduling solution, and then sends the optimal scheduling solution to the output module, including the following steps: The iteration module repeats the operation steps of the selection module, the crossover module, and the mutation module to perform iterative operations. When the number of iteration operations is equal to the number threshold, a new generation of scheduling scheme population is generated; Calculate and obtain the fitness of all new generation scheduling schemes in the new generation scheduling scheme population, and sort all new generation scheduling schemes from large to small according to fitness to generate a scheme sorting table; The new generation scheduling scheme ranked first in the scheme ranking table is taken as the optimal scheduling scheme.

6. An artificial intelligence control system according to claim 5, characterized in that: The output module converts the optimal scheduling scheme into a control code, comprising the following steps: Obtain the optimal scheduling plan from the iteration module. The optimal scheduling plan includes the working time period of each device; Convert the extracted scheduling information into a code format executed by the control module, including converting time information and device identification into corresponding control commands; Generate control codes according to the converted format, including equipment start, stop, and adjustment of working time; The control module automatically controls the operation of the dust suppression equipment at the construction site according to the control code, comprising the following steps: The device identification, start time and stop time are received through the device control function, and the device operation is controlled.

7. An artificial intelligence control system according to claim 6, characterized in that: The selection module generates a next generation scheduling solution, and when the number of the generated next generation scheduling solutions exceeds the number threshold, sending the next generation scheduling solution to the cross module includes the following steps: After obtaining the fitness of all initial scheduling solutions, calculate the fitness ratio ΔS of each initial scheduling solution, the expression is: ΔS = g s / z s , where g s is the fitness of the initial scheduling solution, z s is the total fitness; Use the roulette wheel selection method to select the initial scheduling plan according to the fitness ratio; Generate a random number using a random number generator Assume that the fitness ratios of all initial scheduling schemes are ΔS1, ΔS2, ΔS3, ..., ΔS n , n is the number of initial scheduling solutions, and n is a positive integer; The fitness ratio cumulative probability of the first initial scheduling scheme is FL1 = ΔS1, the fitness ratio cumulative probability of the second initial scheduling scheme is FL2 = ΔS1 + ΔS2, and the fitness ratio cumulative probability of the nth initial scheduling scheme is FL2 = ΔS1 + ΔS2 + ΔS3 + ... + ΔS n ; Set the first fitness ratio cumulative probability ≥ random number The initial scheduling scheme is used as the next generation scheduling scheme.

8. An artificial intelligence control system according to claim 7, characterized in that: The calculation expression of the fitness function is: In the formula, g s is the fitness of the initial scheduling scheme, CD is the dust concentration at the construction site when the initial scheduling scheme is used, ω1 is the weight of the dust concentration at the construction site when the initial scheduling scheme is used, NH is the energy consumption when the initial scheduling scheme is used, ω2 is the energy consumption weight when the initial scheduling scheme is used, and ω1>ω2>0.

9. An artificial intelligence control system according to claim 8, characterized in that: The crossover module performs crossover operation on the next generation scheduling scheme, and generating a new scheduling scheme includes the following steps: Determine the time point of the crossover operation, from which the information of the two next generation scheduling schemes will be crossed; The information of two next-generation scheduling schemes is cut at the intersection point by single-point crossover, and cross-combined to obtain a new scheduling scheme; Repeat the above steps until the new scheduling scheme reaches the predetermined number and then stop the crossover operation.

10. An artificial intelligence control system according to claim 9, characterized in that: The mutation module performs mutation operation on the new scheduling scheme, and the introduction of randomness includes the following steps: Determine the time point of the mutation operation and mutate the new scheduling plan near this time point; Perform mutation operations on the new scheduling plan information near the time point; The new scheduling scheme is mutated to generate a new generation of scheduling scheme; Repeat the above steps until the number of new generation scheduling solutions reaches the predetermined number and then stop the mutation operation.

Images