Green intelligent signal stabilizing and amplifying device for construction complex scene recognition

Abstract

The invention provides a green intelligent signal stabilizing and amplifying device for construction complex scene recognition. The system specifically comprises a solar power generation and energy storage system, an environment perception and identification system, a signal amplifier and an intelligent control system. Photoelectric conversion and electric energy storage are completed through the solar power generation and energy storage system, energy is supplied to the signal amplification and optimization device, parameter detection and corresponding complex scene type identification are carried out on construction site environment factors through the environment perception and identification system, and then on the basis of the identified environment parameters, through algorithm analysis of the intelligent control system, the real-time monitoring of the construction site is realized. The optimal signal quality (signal-to-noise ratio (SNR)) is taken as an optimization target, the regulation and control unit continuously adjusts the gain of the signal amplifier, and finally stable transmission of the signal is realized. Compared with the prior art, solar energy is used for supplying energy to the system, and the anti-interference capability of signals in the complex construction environment can be achieved.

Description

Technical Field

[0001] The present invention relates to the field of building construction technology, and specifically to a green intelligent signal stabilization and amplification device for complex construction scene recognition. The device integrates green energy technology, environmental perception technology, signal processing technology and intelligent control technology, and aims to solve the problems of unstable and susceptible to interference signal transmission caused by the complex and changeable environment at the construction site, and to improve the information level and efficiency of construction management. Background Art

[0002] With the rapid development of the construction industry, the management of construction sites is increasingly dependent on information and intelligent means. However, construction sites often face complex and changeable environmental conditions, such as electromagnetic interference, signal blocking, weather changes, etc. These factors seriously restrict the stability and reliability of wireless communication signals (such as Wi-Fi, Bluetooth, Zigbee, etc.), resulting in data transmission delays, packet loss and even interruptions, affecting the normal operation of key functions such as construction monitoring, personnel scheduling, and remote equipment control.

[0003] Although traditional signal amplification equipment can enhance signal strength to a certain extent, it often lacks the ability to intelligently perceive environmental factors and dynamically adjust, making it difficult to adapt to the complex and changing environment of the construction site. In addition, most traditional equipment relies on power grid power supply, which not only increases construction costs, but also may face power supply inconvenience in remote or temporary construction sites.

[0004] Therefore, developing an intelligent signal stabilization and amplification device that can automatically identify complex construction scenes, dynamically adjust signal gain, and achieve green energy supply is of great significance for improving the information level and work efficiency of the construction site. The present invention is proposed to solve the above problems. By integrating solar power generation and energy storage system, environmental perception and identification system, signal amplifier, adjustment unit and intelligent control system, the stable transmission of signals and the improvement of anti-interference ability are achieved. Summary of the invention

[0005] Purpose of the invention: In response to the problems pointed out in the background technology, the present invention discloses a green intelligent signal stabilization and amplification device for complex construction scene identification, which realizes self-sufficient green energy supply through solar power generation and energy storage system, and uses environmental perception and recognition system to accurately capture the complex and changeable environmental factors of the construction site, combined with the algorithm optimization of the intelligent control system, and dynamically adjusts the gain of the signal amplifier to significantly improve the stability and anti-interference ability of wireless communication signals in complex construction environments.

[0006] Technical solution: The present invention discloses a green intelligent signal stabilization and amplification device for complex construction scene recognition, including a solar power generation and energy storage system, an environmental perception and recognition system, a signal amplifier and an intelligent control system;

[0007] Solar power generation and energy storage system provides continuous energy supply and energy storage for green intelligent signal stabilization and amplification devices for complex construction scene recognition;

[0008] Environmental perception and recognition system, including humidity sensors and dust concentration sensors, to detect specific parameters of humidity and dust in the construction environment; surveillance cameras to monitor the construction environment; real-time collection of environmental data at the construction site, including humidity, dust concentration, and environmental images;

[0009] The intelligent control system receives environmental data from the environmental perception and recognition system, identifies the type of complex construction environment through the scene recognition algorithm, and optimizes and analyzes the signal quality using the backpack group intelligent optimization algorithm, and adjusts the signal amplifier power gain coefficient to ensure that the signal quality, that is, the signal-to-noise ratio (SNR), reaches the optimal level;

[0010] The signal amplifier receives and amplifies the signal from the intelligent control system, adjusts its own gain according to the control instructions of the intelligent control system, and amplifies the signal.

[0011] Furthermore, the intelligent control system takes the best signal-to-noise ratio as the optimization goal, and sets the objective function as:

[0012]

[0013] Among them, SNR is the signal-to-noise ratio, which is used to describe the quality of the signal; α is the signal transmission coefficient, which is related to the signal transmission material and is a constant; P is the power of the signal, which indicates the amount of energy emitted by the signal source; G is the signal amplifier power gain coefficient, which is a variable to be adjusted by the intelligent control system and is used to amplify the signal strength; β is the temperature influence factor, which indicates the degree of influence of temperature on the signal transmission quality and is a constant; T is the current measured temperature value, which is the data monitored in real time by the environmental perception and recognition system; T0 is the initial set temperature value, which is a reference value used to calculate the impact of temperature changes on the signal; γ is the humidity influence factor, which indicates the degree of influence of humidity on the signal transmission quality and is a constant; H is the current measured ambient humidity value; H0 is the preset initial humidity value, which is used to calculate the impact of humidity changes on the signal; N is the power of external noise, which indicates the strength of the interference signal in the environment.

[0014] Furthermore, the backpack group intelligent optimization algorithm is used to adjust the signal amplifier power gain coefficient G to achieve stable signal transmission, and the steps are as follows:

[0015] Step (1) Population initialization: set the maximum number of iterations, upper and lower limits, and set the search space according to the upper and lower limits;

[0016] Step (2) Before the vesicles perform jet propulsion, they need to avoid conflicts among search individuals. In order to avoid conflicts among individuals, they calculate a new position vector:

[0017] A=G / M

[0018] Among them, G represents gravity, and M represents the social force between search individuals;

[0019] M=P min +c1(P max -P min ),

[0020] Among them, P min represents the minimum value of social activities, P max represents the maximum value of social activities, c1 represents a random number between 0 and 1;

[0021] Step (3) Avoid conflicts between adjacent individuals and search for the best neighbor. Calculate the distance between the search individual and the food source, which corresponds to the difference between the expected parameter value of the signal-to-noise ratio achieved in the construction scenario and the signal-to-noise ratio that can be achieved by the current environmental signal amplifier gain. At the tth iteration, the distance between the i-th individual and the food source is,

[0022]

[0023] Where rand is a randomly distributed number between 0 and 1. is the location of the food source of the population at the tth iteration, that is, the optimal individual position of the current population, is the position of the i-th individual given skin in the population at the t-th iteration, and the search individual moves to the position of the best food source. The specific formula is:

[0024]

[0025] A is the position vector of the individual to avoid conflict calculation, is the distance between the current i-th individual and the food source;

[0026] Step (4) Group behavior: After avoiding conflicts and calculating the distance between individuals and the food source, the tunicate individuals adopt group behavior to gather toward the food source, i.e., they begin to send instructions to the signal amplifier through the adjustment unit, and adjust the gain of the amplifier through the following formula, so that the signal-to-noise ratio can achieve the expected effect. The formula for defining the group behavior of tunicates to approach the optimal food source is as follows:

[0027]

[0028] in, It represents the updated position of the tunicate individuals of the previous generation relative to the food source, and c1 represents a random number between 0 and 1.

[0029] Step (5) memory search strategy. Tunicates have a certain memory ability during group foraging. For the special environment of complex construction scenes, they can remember the historical environmental parameter values ​​through environmental recognition. When the same situation is encountered next time, the intelligent control system can directly adjust from the vicinity of the historical value, so that the control strategy can be adjusted quickly and accurately. As the number of times increases, a model database is formed. With the establishment of the data model, the system's anti-interference ability is gradually improved. The search method is:

[0030]

[0031] represents the memory value at the tth iteration, rand() is a uniformly randomly distributed number between 0 and 1, is the position of the i-th tunicate individual in the population at the t-th iteration, It represents the updated position of the tunicate individuals of the previous generation relative to the food source;

[0032] Step (6) determines whether the maximum number of iterations or the threshold range has been reached. If the iteration cycle is not satisfied, returns to step (3);

[0033] Step (7) outputs the optimal position for the tunicate to obtain food, that is, adjusts the amplifier gain to achieve the optimal signal-to-noise ratio.

[0034] Furthermore, based on the population initialization of Singer mapping, the more evenly the initial population is distributed in the solution space in step (1), the greater the probability that the algorithm will find the optimal value. In order to enhance the distribution of the quilt group in the entire solution space, the Singer mapping is introduced to replace the random search strategy in the quilt group algorithm TSA to initialize the quilt group. The iterative formula of Singer mapping is:

[0035]

[0036] The n+1th chaos value, The nth chaotic value, μ∈[0.9,1.08].

[0037] Furthermore, the solar power generation and energy storage system includes solar panels and batteries. The solar panels convert sunlight energy into electrical energy, and the batteries are used to store electrical energy so as to provide power to the entire device when needed.

[0038] Beneficial effects:

[0039] The present invention realizes self-sufficient green energy supply through solar power generation and energy storage system, and uses environmental perception and recognition system to accurately capture complex and changeable environmental factors at the construction site, and dynamically adjusts the gain of the signal amplifier in combination with the algorithm optimization of the intelligent control system, so as to significantly improve the stability and anti-interference ability of wireless communication signals in complex construction environments. This not only effectively solves the problem of poor performance of traditional signal amplification equipment in complex environments, but also provides more reliable technical support for the information management of construction sites, and further promotes scientific and technological innovation and green development in the field of construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The overall block diagram of the system of the present invention is as follows;

[0041] Figure 2 It is a flow chart of the system of the present invention;

[0042] Figure 3 This is a flow chart of adjusting the gain of a signal amplifier using the singer mapping backpack group intelligent optimization algorithm of the present invention. DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0044] The present invention discloses a green intelligent signal stabilization and amplification device for complex construction scene recognition. Figure 1 Specifically, it includes solar power generation and energy storage system, environmental perception and recognition system, signal amplifier, control unit and intelligent control system.

[0045] Solar power generation and energy storage system, which includes solar panels and batteries. The solar panels are responsible for converting sunlight into electrical energy, while the batteries are used to store this electrical energy so as to provide power to the entire device when needed. It provides a continuous and green energy supply for the green intelligent signal stabilization and amplification device for complex construction scene recognition, and enhances the self-sufficiency of the system.

[0046] The environmental perception and recognition system includes a data detection module and an environmental detection module. The data detection module includes a humidity sensor and a dust concentration sensor to detect the specific parameters of humidity and dust in the construction environment. The environmental detection module includes a monitoring camera (environmental monitoring camera) to monitor the construction environment. Through these sensors and cameras, environmental data of the construction site, such as humidity, dust concentration, environmental images, etc., are collected in real time to provide basic data for subsequent complex scene type recognition.

[0047] The intelligent control system includes a scene recognition algorithm and an algorithm analysis module. The system receives data from the environmental perception and recognition system, identifies the type of complex construction environment through the scene recognition algorithm, and optimizes the signal quality using the algorithm analysis module. Based on the analysis results, the control unit controls the gain of the signal amplifier to ensure that the signal quality (signal-to-noise ratio SNR) is optimal and stable signal transmission is achieved.

[0048] Signal amplifier, this module is responsible for receiving and amplifying the signal from the intelligent control system. According to the control instructions of the intelligent control system, it adjusts its own gain and amplifies the signal to overcome the signal attenuation and interference in the complex construction environment and ensure the stability and clear transmission of the signal.

[0049] In summary, the various modules work together to achieve signal stabilization and amplification functions in complex construction scenarios. At the same time, solar energy is used to power the system, which improves the greenness and self-sufficiency of the system.

[0050] The environmental perception and recognition system is used to conduct real-time monitoring and parameter collection of complex construction environments, mainly targeting obstacles to signal transmission caused by weather such as dust and humidity. The intelligent control system is used to perform scene recognition, and the algorithm is used to analyze the current environmental parameters. The signal-to-noise ratio is used as the optimization goal, and the gain of the signal amplifier is adjusted through the adjustment unit, ultimately achieving stable signal transmission and quality assurance.

[0051] In this embodiment, the signal amplifier gain is adjusted by using the Singer mapping backpack group intelligent optimization algorithm to achieve stable signal transmission, and the steps are as follows:

[0052] Step (1) Population initialization: Set the maximum number of iterations of the algorithm, the upper and lower limits, and set the search space of the algorithm according to the upper and lower limits; set the objective function to:

[0053]

[0054] The function takes into account multiple factors such as signal power, signal transmission coefficient, signal amplifier power gain coefficient, external noise power, temperature influence factor and humidity influence factor.

[0055] SNR: Signal-to-noise ratio, used to describe the quality of the signal.

[0056] α: Signal transmission coefficient, which is related to the signal transmission material and is a constant, usually determined through experiments or simulations.

[0057] P: The power of the signal, which indicates the amount of energy emitted by the signal source.

[0058] G: The power gain coefficient of the signal amplifier is the variable that we need to adjust through the intelligent control system to amplify the signal strength.

[0059] β: Temperature influence factor, which indicates the influence of temperature on signal transmission quality. It is a constant obtained by fitting experimental data.

[0060] T: The currently measured temperature value is the data monitored in real time by the environmental perception and recognition system.

[0061] T0: Initial set temperature value, which is a reference value used to calculate the impact of temperature changes on the signal.

[0062] γ: Humidity influence factor, which indicates the influence of humidity on signal transmission quality. It is a constant and is also obtained by fitting experimental data.

[0063] H: The currently measured ambient humidity value, which is also the data monitored in real time by the environmental perception and recognition system.

[0064] H0: Preset initial humidity value, used to calculate the impact of humidity changes on the signal.

[0065] N: The power of external noise, indicating the strength of the interference signal in the environment.

[0066] Step (2) Before the vesicles perform jet propulsion, they need to avoid conflicts among search individuals. In order to avoid conflicts among individuals, they calculate a new position vector:

[0067] A=G / M

[0068] Where G represents gravity and M represents the social force between searching individuals.

[0069] M=P min +c1(P max -P min ),

[0070] Among them, P min represents the minimum value of social activities, P max represents the maximum value of social activity, and c1 represents a random number between 0 and 1.

[0071] Step (3) To avoid conflicts between adjacent individuals, the search individual moves towards the best neighbor. At this time, it is necessary to calculate the distance between the search individual and the food source, which corresponds to the difference between the expected parameter value of the signal-to-noise ratio achieved in the construction scenario and the signal-to-noise ratio that can be achieved by the current environmental signal amplifier gain. At the tth iteration, the distance between the i-th individual and the food source is,

[0072]

[0073] Where rand is a randomly distributed number between 0 and 1. is the location of the food source of the population at the tth iteration, that is, the optimal individual position of the current population, is the position of the i-th individual given skin in the population at the t-th iteration, and the search individual moves to the position of the best food source. The specific formula is:

[0074]

[0075] A is the position vector of the individual to avoid conflict calculation, is the distance between the current i-th individual and the food source.

[0076] Step (4) Group behavior: After avoiding conflicts and calculating the distance between individuals and the food source, the tunicate individuals adopt group behavior to gather towards the food source, i.e., they begin to send instructions to the signal amplifier through the adjustment unit, and adjust the gain of the amplifier through the following formula, so that the signal-to-noise ratio can achieve the expected effect. The formula that defines the group behavior of tunicates to approach the optimal food source is as follows:

[0077]

[0078] in, It represents the updated position of the tunicate individuals of the previous generation relative to the food source, and c1 represents a random number between 0 and 1.

[0079] Step (5) Memory search strategy. Tunicates have a certain memory ability during group foraging. Therefore, in addition to learning from individuals in the field, they can also search the field of other individuals' historical optimal positions with a certain probability to strengthen the full search of individual historical positions. For special environments in complex construction scenes, such as dust and humidity, environmental recognition can memorize historical environmental parameter values. When the same situation is encountered next time, the intelligent control system can directly adjust from the vicinity of the historical value, so that the control strategy can be quickly and accurately adjusted. As the number of times increases, a model database can be formed. As the data model is established, the system's anti-interference ability is gradually improved. The search method is:

[0080]

[0081] represents the memory value at the tth iteration, rand() is a uniformly randomly distributed number between 0 and 1, is the position of the i-th tunicate individual in the population at the t-th iteration, Represents the updated position of the tunicate individuals of the previous generation relative to the food source.

[0082] Step (6) is based on the population initialization of Singer mapping. The more evenly the initial population in step (1) is distributed in the solution space, the greater the probability that the algorithm will find the optimal value. The chaotic mapping strategy is widely used in the initial population generation of swarm intelligence optimization algorithms due to its ergodic and non-repetitive characteristics. Therefore, in order to enhance the distribution of the tunicate group in the entire solution space, the Singer mapping is introduced to replace the random search strategy in the tunicate swarm algorithm TSA (Tunicate Swarm Algorithm) to initialize the tunicate group. The iterative formula of the Singer mapping is:

[0083]

[0084] The n+1th chaos value, The nth chaotic value, μ∈[0.9,1.08].

[0085] Step (7) determines whether the maximum number of iterations or the threshold range has been reached. If the iteration cycle is not satisfied, return to step (3);

[0086] Step (8) outputs the optimal position for the tunicate to obtain food, that is, adjusts the amplifier gain to achieve the optimal signal-to-noise ratio.

[0087] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent transformation or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. A green intelligent signal stabilization and amplification device for complex construction scene recognition, characterized in that: Including solar power generation and energy storage system, environmental perception and recognition system, signal amplifier and intelligent control system; Solar power generation and energy storage system provides continuous energy supply and energy storage for green intelligent signal stabilization and amplification devices for complex construction scene recognition; Environmental perception and recognition system, including humidity sensors and dust concentration sensors, to detect specific parameters of humidity and dust in the construction environment; surveillance cameras to monitor the construction environment; real-time collection of environmental data at the construction site, including humidity, dust concentration, and environmental images; The intelligent control system receives environmental data from the environmental perception and recognition system, identifies the type of complex construction environment through the scene recognition algorithm, and optimizes and analyzes the signal quality using the backpack group intelligent optimization algorithm, and adjusts the signal amplifier power gain coefficient to ensure that the signal quality, that is, the signal-to-noise ratio (SNR), reaches the optimal level; The signal amplifier receives and amplifies the signal from the intelligent control system, adjusts its own gain according to the control instructions of the intelligent control system, and amplifies the signal.

2. According to claim 1, a green intelligent signal stabilization and amplification device for complex construction scene recognition is characterized in that: The intelligent control system takes the best signal-to-noise ratio as the optimization goal, and sets the objective function as: Among them, SNR is the signal-to-noise ratio, which is used to describe the quality of the signal; α is the signal transmission coefficient, which is related to the signal transmission material and is a constant; P is the power of the signal, which indicates the amount of energy emitted by the signal source; G is the power gain coefficient of the signal amplifier, which is a variable to be adjusted by the intelligent control system and is used to amplify the strength of the signal; β is the temperature influence factor, which indicates the degree of influence of temperature on the signal transmission quality and is a constant; T is the currently measured temperature value, which is the data monitored in real time by the environmental perception and recognition system; T0 is the initial set temperature value, which is a reference value used to calculate the impact of temperature changes on the signal; γ is the humidity influence factor, which indicates the degree of influence of humidity on the signal transmission quality and is a constant; H is the currently measured ambient humidity value; H0 is the preset initial humidity value, which is used to calculate the impact of humidity changes on the signal; N is the power of external noise, which indicates the strength of the interference signal in the environment.

3. According to claim 2, a green intelligent signal stabilization and amplification device for complex construction scene recognition is characterized in that: The backpack group intelligent optimization algorithm is used to adjust the signal amplifier power gain coefficient G to achieve stable signal transmission. The steps are as follows: Step (1) Population initialization: set the maximum number of iterations, upper and lower limits, and set the search space according to the upper and lower limits; Step (2) Before the vesicles perform jet propulsion, they need to avoid conflicts among search individuals. In order to avoid conflicts among individuals, they calculate a new position vector: A=G / M Among them, G represents gravity, and M represents the social force between search individuals; M=P min +c1(P max -P min ), Among them, P min represents the minimum value of social activities, P max represents the maximum value of social activities, c1 represents a random number between 0 and 1; Step (3) Avoid conflicts between adjacent individuals and search for the best neighbor. Calculate the distance between the search individual and the food source, which corresponds to the difference between the expected parameter value of the signal-to-noise ratio achieved in the construction scenario and the signal-to-noise ratio that can be achieved by the current environmental signal amplifier gain. At the tth iteration, the distance between the i-th individual and the food source is, Where rand is a randomly distributed number between 0 and 1. is the location of the food source of the population at the tth iteration, that is, the optimal individual position of the current population, is the position of the i-th individual given skin in the population at the t-th iteration. The search individual moves to the position of the best food source. The specific formula is: A is the position vector of the individual to avoid conflict calculation, is the distance between the current i-th individual and the food source; Step (4) Group behavior: After avoiding conflicts and calculating the distance between individuals and the food source, the tunicate individuals adopt group behavior to gather toward the food source, i.e., they begin to send instructions to the signal amplifier through the adjustment unit, and adjust the gain of the amplifier through the following formula, so that the signal-to-noise ratio can achieve the expected effect. The formula for defining the group behavior of tunicates to approach the optimal food source is as follows: in, It represents the updated position of the tunicate individuals of the previous generation relative to the food source, and c1 represents a random number between 0 and 1. Step (5) memory search strategy. Tunicates have a certain memory ability during group foraging. For the special environment of complex construction scenes, they can remember the historical environmental parameter values ​​through environmental recognition. When the same situation is encountered next time, the intelligent control system can directly adjust from the vicinity of the historical value, so that the control strategy can be adjusted quickly and accurately. As the number of times increases, a model database is formed. With the establishment of the data model, the system's anti-interference ability is gradually improved. The search method is: represents the memory value at the tth iteration, rand() is a uniformly randomly distributed number between 0 and 1, is the position of the i-th tunicate individual in the population at the t-th iteration, It represents the updated position of the tunicate individuals of the previous generation relative to the food source; Step (6) determines whether the maximum number of iterations or the threshold range has been reached. If the iteration cycle is not satisfied, returns to step (3); Step (7) outputs the optimal position for the tunicate to obtain food, that is, adjusts the amplifier gain to achieve the optimal signal-to-noise ratio.

4. According to claim 3, a green intelligent signal stabilization and amplification device for complex construction scene recognition is characterized in that: Population initialization based on Singer mapping. For step (1), the more evenly the initial population is distributed in the solution space, the greater the probability that the algorithm will find the optimal value. In order to enhance the distribution of the quilt group in the entire solution space, the Singer mapping is introduced to replace the random search strategy in the quilt group algorithm TSA to initialize the quilt group. The iterative formula of the Singer mapping is: The n+1th chaos value, The nth chaotic value, μ∈[0.9,1.08].

5. A green intelligent signal stabilization and amplification device for complex construction scene recognition according to claim 1, characterized in that: The solar power generation and energy storage system includes solar panels and batteries. The solar panels convert sunlight energy into electrical energy, and the batteries are used to store electrical energy so as to provide power to the entire device when needed.

Images