Highway tunnel illumination energy consumption optimization method based on penalty function-particle swarm algorithm
Through the penalty function-particle swarm algorithm, the local optimal problem of the multi-parameter multi-constraint model is solved, and the global optimal solution and precise energy saving are achieved, and the energy consumption minimization is achieved based on lighting safety is obtained. Layout parameters.
Patent Information
- Application Number
- CN202411084584.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-11-12
AI Technical Summary
The existing highway tunnel lighting energy consumption optimization model is prone to falling into local optimization when dealing with multi-parameter and multi-constraint nonlinear models, resulting in insufficient computational accuracy and global optimization, and the effective balance between lighting safety and energy saving cannot be achieved.
Using the method based on the penalty function-particle swarm algorithm, by establishing a tunnel lighting parameter calculation model and optimization model, using the particle swarm intelligent optimization algorithm to solve iteratively, optimize the lamp layout parameters to minimize lighting energy consumption, and meet the lighting safety threshold at the same time, avoid local The optimal trap.
The global optimal solution in the feasible domain is realized, the calculation accuracy is improved, and the energy consumption is minimized based on lighting safety is ensured, and it has strong practicality and accuracy.
Smart Images

Figure CN118940637A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of highway tunnel lighting and relates to a highway tunnel lighting energy consumption optimization method based on penalty function-particle swarm algorithm. Background Art
[0002] The contradiction between lighting safety and energy saving in highway tunnel lighting is becoming increasingly prominent. The energy consumption of highway tunnel lighting is closely related to the lighting layout parameters. Most of the existing highway tunnel lighting energy consumption optimization models are based on the control variable method, which optimizes the lighting energy consumption for a single independent lighting layout parameter. However, the tunnel lighting calculation model is actually a nonlinear model composed of multiple parameters and multiple constraints. The interaction between parameters will have a great impact on the calculation results. The traditional lighting energy consumption optimization model may cause the optimization effect to be inconsistent with the actual lighting effect, and the calculation accuracy is poor.
[0003] On the other hand, traditional optimization algorithms, such as conjugate gradient descent and Newton's method, are prone to local optimality when dealing with nonlinear models of tunnel lighting with multiple parameters and multiple constraints, and cannot find the global optimal solution in the feasible domain. Therefore, the existing highway tunnel lighting energy consumption optimization methods have certain limitations in terms of accuracy and global optimality.
[0004] The present invention aims to provide a highway tunnel lighting energy consumption optimization method based on penalty function-particle swarm algorithm to solve the problems existing in the prior art and achieve an optimal balance between lighting safety and energy saving. Summary of the invention
[0005] In view of this, the object of the present invention is to provide a method for optimizing energy consumption of highway tunnel lighting based on penalty function-particle swarm algorithm.
[0006] In order to achieve the above object, the present invention provides the following technical solutions:
[0007] A highway tunnel lighting energy consumption optimization method based on penalty function-particle swarm algorithm, the method comprises the following steps:
[0008] Establish a tunnel lighting parameter calculation model, which describes the relationship between lamp layout parameters and road lighting brightness;
[0009] The penalty function-particle swarm optimization algorithm is used to establish a lighting energy consumption optimization model;
[0010] In the optimization model, the lighting height, spacing, and elevation angle are used as control parameters;
[0011] The penalty function-particle swarm optimization algorithm is used to iteratively solve the lamp layout parameters with the minimum lighting energy consumption.
[0012] Furthermore, the tunnel lighting parameter calculation model is established as follows:
[0013] In the highway tunnel, the lights are arranged symmetrically on both sides. For a point p on the road surface, its illuminance value is provided by the four nearest lamp sources A1, A2, A3, and A4. W is the road surface width, S is the vertical spacing of the lights, D is the horizontal spacing of the lights, and H is the height of the lights. Taking the intersection of two lamps and the center line of the road surface as the origin to establish a coordinate system, and choosing the road surface between two lamps as the calculation area, the coordinates of point p are (x, y), where -S / 2 < x < S / 2 and -D / 2 < y < D / 2. The relationship between the total power of tunnel lighting, the layout parameters of the lamps, and the road surface lighting brightness will be mathematically deduced to form a conversion model, as shown in Equations (1) to (7).
[0014] For a point p on the road surface of the highway tunnel, the calculation formula for the luminous intensity generated by lamp A i , i = 1, 2, 3, 4 for it is shown in Equation (1).
[0015]
[0016] In the formula: P is the lighting power of the lamp; t is the lighting time; I(γ i ) is the luminous intensity value at point p; γ i is the incident angle of the light from lamp A i at point p; η is the utilization coefficient of the lamp; M is the maintenance coefficient of the lamp; γ i The calculation of the angle size is shown in Equation (2).
[0017]
[0018] According to the "Code for Highway Tunnel Lighting Design", the illuminance E pi corresponding to point p of lamp i is calculated according to Equation (3):
[0019]
[0020] In the formula: ξ is the elevation angle of the lamp; the horizontal spacing D of the lights is related to the tunnel height h, the lamp height H, and the tunnel width W, and is calculated by Equation (4).
[0021]
[0022] The E p of all lamps at point p and the average road surface illuminance E av are calculated according to Equation (5).
[0023]
[0024] From Equations (1) to (5), the lighting power P of the lamp and the average road surface illuminance E avAnd the relationship between the lighting layout parameters, namely the vertical spacing S of the lighting layout, the height H of the lighting layout, and the elevation angle ξ of the lighting fixture, is expressed as formula (6);
[0025] P=E av ·f(S,H,ξ) (6)
[0026] Tunnel lighting energy consumption F and average road illumination E av And the relationship between the lighting layout parameters, namely the vertical spacing S of the lighting layout, the height H of the lighting layout, and the elevation angle ξ of the lighting fixture, is shown in formula (7);
[0027]
[0028] The above calculation model is used to obtain the relationship between tunnel lighting energy consumption, average road surface illumination and the layout parameters of each lamp.
[0029] 3. The method for optimizing highway tunnel lighting energy consumption based on penalty function-particle swarm optimization algorithm according to claim 1, characterized in that the penalty function-particle swarm optimization algorithm comprises the following steps:
[0030] Randomly generate multiple particles within the feasible domain of lighting parameters;
[0031] Calculate the fitness value of each particle, i.e., the tunnel lighting energy consumption;
[0032] Adjust the search speed direction and size of each particle through the individual optimal position and the global optimal position;
[0033] Iteratively update the particle's velocity and position until the global optimal solution is found.
[0034] Furthermore, the lighting energy consumption optimization model is established as follows:
[0035] The particle swarm intelligent optimization algorithm is used to optimize the tunnel lighting energy consumption. In the particle swarm algorithm, X is a three-dimensional variable containing three lighting parameter variables, namely, the vertical spacing S of the lighting, the height H of the lighting, and the elevation angle ξ of the lighting fixture. m particles are randomly generated in the feasible domain of X. The position of each particle represents a feasible solution. The quality of each particle depends on the fitness value of the objective function of the problem to be optimized, namely, the tunnel lighting energy consumption F. The tunnel lighting energy consumption optimization model is established:
[0036]
[0037] The feasible domain of X must meet the design values of road surface illumination E0, road surface illumination uniformity U0, and road surface centerline illumination longitudinal uniformity U1 required by the "Highway Tunnel Lighting Design Specifications" to ensure tunnel lighting safety, as shown in formula (9);
[0038]
[0039] In the formula, E min The minimum illumination of the road surface in the calculation area; E' min and E' max are the minimum and maximum illumination of the road centerline in the calculation area respectively; v is the design vehicle speed;
[0040] The penalty function method is used to transform the constrained optimization model described by equations (8) and (9) into an unconstrained optimization model. The new model is defined as:
[0041]
[0042] Where M is the penalty factor;
[0043] Each particle continuously adjusts its search speed direction and size through its own optimal position and the global optimal position to make itself closer to the global optimal solution; when the global optimal solution is the optimal solution of the entire feasible domain, the iteration stops; let the position of the kth particle be X k =[S k ,H k ,ξ k ], speed is V k =[V Sk ,V Hk ,V ξk ], the individual optimal position found by the kth particle in the search, that is, the individual optimal solution is X bestk =[S bestk ,H bestk ,ξ bestk ], the corresponding fitness function, that is, the tunnel lighting energy consumption is F bestk ;
[0044] During the iteration process, the velocity and position of the particle at the j+1th iteration are calculated and updated according to formula (11);
[0045]
[0046] Where, k = 1, 2, ..., m; j is the number of iterations; r1 and r2 are random numbers in [0, 1], c1 is the individual learning factor, and c2 is the global learning factor; w is the inertia weight of the speed. In order to prevent the optimization model from falling into the local optimum, w is set by formula (12) so that the model has better global search ability in the early stage and better local search ability in the later stage.
[0047]
[0048] In the formula, w max and w min are the pre-given maximum and minimum inertia weights, which are 0.9 and 0.4; maxgen is the maximum number of iterations, Ggeneration is the current iteration number;
[0049] After the iteration, the global optimal solution X of the entire population in the feasible domain is obtained. best =[S best ,H best ,ξ best ] and the corresponding fitness function F best , that is, the tunnel lighting energy consumption is F best When the lighting energy consumption is minimized while ensuring lighting safety, the vertical spacing of the lamps is S best , the height of the lamp is H best , the lamp elevation angle is ξ best .
[0050] Furthermore, the tunnel lighting parameter calculation model includes calculating the illumination value of point p, which is provided by the nearest four lamp light sources.
[0051] Furthermore, the lighting safety threshold includes road surface illumination, road surface illumination uniformity and road surface centerline illumination longitudinal uniformity.
[0052] Furthermore, the penalty function-particle swarm optimization algorithm balances the global search capability and the local search capability by adjusting the inertia weight.
[0053] The beneficial effects of the present invention are:
[0054] (1) The penalty function-particle swarm optimization algorithm is used to effectively solve the problem that traditional optimization algorithms are prone to fall into local optimality in the nonlinear model of tunnel lighting with multiple parameters and multiple constraints, and a global optimal solution is achieved within the feasible domain.
[0055] (2) By establishing a tunnel lighting energy consumption optimization model that couples multiple lighting parameters, the calculation accuracy is improved and the effect of precise energy saving and carbon reduction is achieved.
[0056] (3) The lighting layout parameters that minimize lighting energy consumption while ensuring tunnel lighting safety were obtained, which is convenient for guiding actual engineering applications and has strong practicality.
[0057] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:
[0059] Figure 1 This is a schematic diagram of the calculation principle of tunnel lighting parameters;
[0060] Figure 2 This is a flowchart for optimizing energy consumption of highway tunnel lighting based on penalty function-particle swarm algorithm. DETAILED DESCRIPTION
[0061] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.
[0062] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.
[0063] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "front", "rear", etc. indicate the orientation or position relationship, they are based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as limiting the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.
[0064] 1. Tunnel lighting parameter calculation model
[0065] Highway tunnels usually use bilateral symmetrical lighting. For point p on the road surface, its illumination value is mainly provided by the nearest four lamp light sources A1, A2, A3 and A4. Figure 1As shown in the figure, in the figure, W is the road surface width, S is the vertical spacing of the lamps, D is the horizontal spacing of the lamps, and H is the height of the lamps. Taking the intersection point of two lamps and the center line of the road surface as the origin and establishing a coordinate system, the road surface between the two lamps is selected as the calculation area, and the coordinates of the calculation point p are (x, y), where -S / 2 < x < S / 2 and -D / 2 < y < D / 2. Next, the relationship between the total power of tunnel lighting, the lamp layout parameters, and the road surface lighting brightness will be mathematically deduced to form a conversion model, as shown in Equations (1) to (7).
[0066] For a point p on the road surface of a highway tunnel, the calculation formula for the luminous intensity generated by lamp A i (i = 1, 2, 3, 4) on it is as shown in Equation (1).
[0067]
[0068] In the formula: P is the lighting power of the lamp; t is the lighting time; I(γ i ) is the luminous intensity value at point p; γ i is the light incident angle of lamp A i at point p; η is the utilization coefficient of the lamp; M is the lamp maintenance coefficient. The size of γ i angle is calculated as shown in Equation (2).
[0069]
[0070] According to the "Code for Highway Tunnel Lighting Design" (JTG / T D70 / 2 - 01 - 2014), the illuminance E pi of lamp i corresponding to point p is calculated according to Equation (3):
[0071]
[0072] In the formula: ξ is the elevation angle of the lamp; the horizontal spacing D of the lamps is related to the tunnel height h, the lamp height H, and the tunnel width W, and is calculated by Equation (4).
[0073]
[0074] The E p of all lamps on point p and the average road surface illuminance E av are calculated according to Equation (5).
[0075]
[0076] From Equations (1) to (5), the relationship between the lighting power P of the lamp, the average road surface illuminance E av and the lamp layout parameters (vertical spacing S of the lamps, lamp height H, elevation angle ξ of the lamp) can be obtained, denoted as Equation (6).
[0077] P = Eav ·f(S,H,ξ) (6)
[0078] Therefore, the tunnel lighting energy consumption F is proportional to the average road illumination E av The relationship between the lighting layout parameters (vertical spacing S, lighting height H, and lighting elevation angle ξ) is shown in formula (7).
[0079]
[0080] Through the above calculation model, we can get the relationship between tunnel lighting energy consumption, average road illumination and the layout parameters of each lamp. The following will be based on the optimization of lighting energy consumption and establish a lamp layout parameter model with the minimum lighting energy consumption under the premise of meeting lighting safety. 2. Tunnel lighting energy consumption optimization model based on penalty function-particle swarm algorithm
[0081] The particle swarm intelligent optimization algorithm is used to optimize the tunnel lighting energy consumption. In the particle swarm algorithm, X is a three-dimensional variable containing three lighting parameter variables (vertical spacing S of lighting, height H of lighting, and elevation angle ξ of lighting fixtures). m particles are randomly generated in the feasible domain of X. The position of each particle represents a feasible solution, and the quality of each particle depends on the fitness value of the objective function of the problem to be optimized, that is, the tunnel lighting energy consumption F. Therefore, a tunnel lighting energy consumption optimization model can be established:
[0082]
[0083] The feasible domain of X must meet the design values of road surface illumination E0, road surface illumination uniformity U0, and road surface centerline illumination longitudinal uniformity U1 required by the "Highway Tunnel Lighting Design Specifications" (JTG / T D70 / 2-01-2014), so as to ensure the safety of tunnel lighting, as shown in formula (9).
[0084]
[0085] In the formula, E min The minimum illumination of the road surface in the calculation area; E' min and E' max are the minimum and maximum illumination of the center line of the road in the calculation area respectively; v is the design vehicle speed.
[0086] The penalty function method is used to transform the constrained optimization model described by equations (8) and (9) into an unconstrained optimization model. The new model is defined as:
[0087]
[0088] Where M is the penalty factor.
[0089] Each particle can continuously adjust its search speed, direction and size through its own optimal position and the global optimal position to make itself closer to the global optimal solution. When the global optimal solution is the optimal solution of the entire feasible domain, the iteration stops. Assume that the position of the kth particle is X k =[S k ,H k ,ξ k ], speed is V k =[V Sk ,V Hk ,V ξk ], the individual optimal position (individual optimal solution) found by the kth particle in the search is X bestk =[S bestk ,H bestk ,ξ bestk ], the corresponding fitness function, that is, the tunnel lighting energy consumption is F bestk .
[0090] During the iteration process, the velocity and position of the particle at the j+1th iteration are calculated and updated according to formula (11).
[0091]
[0092] Where, k = 1, 2, ..., m; j is the number of iterations; r1 and r2 are random numbers in [0, 1], c1 is the individual learning factor, c2 is the global learning factor; w is the inertia weight of the speed. In order to prevent the optimization model from falling into the local optimum, this paper sets w through formula (12) so that the model has better global search ability in the early stage and better local search ability in the later stage.
[0093]
[0094] In the formula, w max and w min are the pre-given maximum and minimum inertia weights, which are generally 0.9 and 0.4; maxgen is the maximum number of iterations, G generation is the current iteration number.
[0095] After the iteration, the global optimal solution X of the entire population in the feasible domain can be obtained. best =[S best ,H best ,ξ best ] and the corresponding fitness function F best , that is, the tunnel lighting energy consumption is F best When the lighting energy consumption is minimized while ensuring lighting safety, the vertical spacing of the lamps is S. best , the height of the lamp is H best , the lamp elevation angle is ξ best .
[0096] In summary, the tunnel lighting energy consumption optimization process based on particle swarm algorithm is as follows: Figure 2 shown.
[0097] Based on the particle swarm optimization algorithm combined with penalty function, this paper establishes a highway tunnel lighting energy consumption optimization model with lighting height, spacing and elevation angle as control parameters and lighting safety threshold in lighting regulations as constraint conditions, aiming to achieve the following objectives:
[0098] (1) In terms of optimization algorithm, the penalty function-particle swarm optimization algorithm is used to solve the problem that traditional optimization algorithms are prone to fall into local optimality in the nonlinear model of tunnel lighting with multiple parameters and multiple constraints, and to achieve the global optimality in the feasible domain;
[0099] (2) In the optimization model, the tunnel lighting energy consumption optimization of multiple lighting parameters is realized, which solves the problem of low calculation accuracy of traditional lighting energy consumption optimization models and achieves the effect of precise energy saving and carbon reduction;
[0100] (3) The lighting layout parameters that minimize lighting energy consumption while ensuring tunnel lighting safety are obtained, which is convenient for guiding actual engineering applications and has strong practicality.
[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.
Claims
1. A highway tunnel lighting energy consumption optimization method based on penalty function-particle swarm algorithm, characterized by: The method includes the following steps: Establish a tunnel lighting parameter calculation model, which describes the relationship between the lamp layout parameters and the road surface lighting brightness; Adopt the penalty function - particle swarm optimization algorithm to establish an illumination energy consumption optimization model; In the optimization model, the lamp installation height, spacing, and elevation angle are used as control parameters; Through iterative solution using the penalty function - particle swarm optimization algorithm, obtain the lamp layout parameters with the minimum illumination energy consumption.
2. The method for optimizing highway tunnel lighting energy consumption based on penalty function-particle swarm algorithm according to claim 1 is characterized in that: The establishment of the tunnel lighting parameter calculation model is specifically as follows: In highway tunnels, lamps are arranged symmetrically on both sides. For a point p on the road surface, its illuminance value is provided by the four nearest lamp sources A1, A2, A3, and A4. W is the road surface width, S is the vertical spacing of lamp installation, D is the horizontal spacing of lamp installation, and H is the lamp installation height; Taking the intersection of two lamps and the center line of the road surface as the origin to establish a coordinate system, and selecting the road surface between two lamps as the calculation area. The coordinates of point p are (x, y), where -S / 2 < x < S / 2 and -D / 2 < y < D / 2; A mathematical derivation will be carried out on the relationship between the total power of tunnel lighting, the lamp layout parameters, and the road surface lighting brightness to form a conversion model, as shown in Equations (1) to (7); For a point p on the road surface of a highway tunnel, the luminaire A i , i=1,2,3,4, the calculation formula of the light intensity generated is shown in formula (1); Where: P is the lighting power of the lamp; t is the lighting time; I(γ i ) is the light intensity value at point p; γ i For lamp A i The angle of incidence of the light ray at point p; η is the utilization coefficient of the lamp; M is the maintenance coefficient of the lamp; γ i The angle is calculated as shown in formula (2); According to the "Highway Tunnel Lighting Design Regulations", the illumination E of lamp i corresponding to point p pi , calculated according to formula (3): In the formula: ξ is the lamp elevation angle; the horizontal spacing D of lamp installation is related to the tunnel height h, lamp height H, and tunnel width W, and is calculated by Equation (4); E of all lamps to point p p And the average road illumination E av , calculated according to formula (5); From equations (1) to (5), we can get the lighting power P of the lamp and the average illuminance E of the road surface: av And the relationship between the lighting layout parameters, namely the vertical spacing S of the lighting layout, the height H of the lighting layout, and the elevation angle ξ of the lighting fixture, is expressed as formula (6); P=E av ·f(S,H,ξ) (6) Tunnel lighting energy consumption F and average road illumination E av And the relationship between the lighting layout parameters, namely the vertical spacing S of the lighting layout, the height H of the lighting layout, and the elevation angle ξ of the lighting fixture, is shown in formula (7); Through the above calculation model, obtain the relationship between the tunnel lighting energy consumption, the average road surface illuminance, and each lamp layout parameter.
3. The highway tunnel lighting energy consumption optimization method based on penalty function-particle swarm algorithm according to claim 1 is characterized in that: The penalty function - particle swarm optimization algorithm includes the following steps: Randomly generate multiple particles within the feasible region of the lamp layout parameters; Calculate the fitness value of each particle, that is, the tunnel lighting energy consumption; Adjust the search speed direction and magnitude of each particle through the individual optimal position and the global optimal position; Iteratively update the speed and position of the particles until the global optimal solution is found.
4. The method for optimizing highway tunnel lighting energy consumption based on penalty function-particle swarm algorithm according to claim 3 is characterized in that: The establishment of the illumination energy consumption optimization model is specifically as follows: Adopt the particle swarm intelligent optimization algorithm to optimize the tunnel lighting energy consumption; in the particle swarm algorithm, X is a three - dimensional variable containing three lamp layout parameter variables, namely the vertical spacing S of lamp installation, the lamp installation height H, and the lamp elevation angle ξ. Randomly generate m particles within the feasible region of X. The position of each particle represents a feasible solution, and the quality of each particle depends on the fitness value of the objective function of the problem to be optimized, that is, the tunnel lighting energy consumption F; Establish a tunnel lighting energy consumption optimization model: The feasible region of X needs to meet the design values of the road surface illuminance E0, road surface illuminance uniformity U0, and longitudinal uniformity U1 of the road surface center line illuminance required by the "Code for Design of Highway Tunnel Lighting" to ensure the safety of tunnel lighting, as shown in Equation (9); In the formula, E min The minimum illumination of the road surface in the calculation area; E' min and E' max are the minimum and maximum illumination of the road centerline in the calculation area respectively; v is the design vehicle speed; Adopt the penalty function method to convert the constrained optimization model described by Equations (8) and (9) into an unconstrained optimization model. The newly established model is defined as: In the formula, M is the penalty factor; Each particle continuously adjusts its search speed direction and size through its own optimal position and the global optimal position to make itself closer to the global optimal solution; when the global optimal solution is the optimal solution of the entire feasible domain, the iteration stops; let the position of the kth particle be X k =[S k ,H k ,ξ k ], speed is V k =[V Sk ,V Hk ,V ξk ], the individual optimal position found by the kth particle in the search, that is, the individual optimal solution is X bestk =[S bestk ,H bestk ,ξ bestk ], the corresponding fitness function, that is, the tunnel lighting energy consumption is F bestk ; During the iteration process, the speed and position of the particle at the (j + 1) - th iteration are calculated and updated according to Equation (11); Where, k = 1, 2, ..., m; j is the number of iterations; r1 and r2 are random numbers in [0, 1], c1 is the individual learning factor, and c2 is the global learning factor; w is the inertia weight of the speed. In order to prevent the optimization model from falling into the local optimum, w is set by formula (12) so that the model has better global search ability in the early stage and better local search ability in the later stage. In the formula, w max and w min are the pre-given maximum and minimum inertia weights, which are 0.9 and 0.4; maxgen is the maximum number of iterations, G generation is the current iteration number; After the iteration, the global optimal solution X of the entire population in the feasible domain is obtained. best =[S best ,H best ,ξ best ] and the corresponding fitness function F best , that is, the tunnel lighting energy consumption is F best When the lighting energy consumption is minimized while ensuring lighting safety, the vertical spacing of the lamps is S best , the height of the lamp is H best , the lamp elevation angle is ξ best .
5. The method for optimizing highway tunnel lighting energy consumption based on penalty function-particle swarm algorithm according to claim 1 is characterized in that: The tunnel lighting parameter calculation model includes calculating the illumination value of a point p, which is provided by the nearest four lamp light sources.
6. The highway tunnel lighting energy consumption optimization method based on penalty function-particle swarm algorithm according to claim 1 is characterized by: The lighting safety threshold includes road surface illumination, road surface illumination uniformity and road surface centerline illumination longitudinal uniformity.
7. The method for optimizing energy consumption of highway tunnel lighting based on penalty function-particle swarm algorithm according to claim 2 is characterized in that: The penalty function-particle swarm optimization algorithm balances the global search capability and the local search capability by adjusting the inertia weight.
