An intelligent lift for building construction and its control system and method

Abstract

The present invention discloses a control system for an intelligent elevator used in construction, including an operation data acquisition unit for acquiring the first operation data of the elevator; a braking distance prediction unit for inputting the first operation data into a prediction model and outputting the braking distance of the elevator; obtaining the operation distance between the cage floor and the target parking level in real time, and judging the size of the distance and the braking distance; when the operation distance is greater than the braking distance, obtaining the second operation data of the elevator in real time to calculate the target operation speed of the elevator, so as to regulate the current operation speed and update the first operation data; a leveling braking control unit for repeatedly calling the braking distance prediction unit until the operation distance is equal to the braking distance, and performing leveling braking control on the elevator according to the latest braking distance. The present invention realizes precise leveling control of the elevator and ensures construction safety by regulating the operation speed in real time and updating the predicted braking distance in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of construction intelligent control, and in particular to an intelligent elevator used in building construction and a control system and method thereof. Background Art

[0002] In the field of construction, construction elevators are necessary equipment for transporting vertical lifting workers. Traditional construction elevators mostly use contactors or relays as switches, and start and stop with primitive methods of direct start and mechanical brakes. The entire process is mostly completed by manual and manual experience control. The cage often fails to level with the target floor after parking, causing a major safety hazard. Therefore, the current start-stop control of the elevator has the disadvantages of low precision, low efficiency, low intelligence, and severe mechanical loss, which makes it difficult to meet the construction requirements of the elevator. Summary of the invention

[0003] In order to solve at least one of the technical problems mentioned above, the present invention provides an intelligent elevator for building construction and a control system and method thereof.

[0004] In a first aspect, the present invention provides a control system for an intelligent lift for construction, the control system comprising:

[0005] An operation data acquisition unit is used to obtain first operation data of the elevator, the first operation data including cage load, operation speed and operation direction;

[0006] The braking distance prediction unit is used to input the first operation data into the trained prediction model and output the braking distance of the elevator; obtain the operation distance between the cage floor and the target parking level in real time, and judge the size of the operation distance and the braking distance; when the operation distance is greater than the braking distance, obtain the second operation data of the elevator in real time, the second operation data includes environmental data, material uniformity and material inclination; calculate the target operation speed of the elevator according to the second operation data, use the target operation speed to adjust the current operation speed, and update the first operation data;

[0007] The leveling brake control unit is used to repeatedly call the braking distance prediction unit until the running distance is equal to the braking distance, and then perform leveling brake control on the elevator according to the current latest braking distance.

[0008] Preferably, the prediction model is obtained by training based on BP neural network algorithm;

[0009] Among them, the momentum term is used to iteratively update the weights in the BP neural network algorithm:

[0010] w(k+1)=w(k)+η(k)[(1-α)D(k)+αD(k-1)]

[0011] η(k)=2 λ η(k-1)

[0012] λ=sgn[D(k)D(k-1)]

[0013] In the formula, k represents the node of the network output layer, w represents the weight, η represents the learning rate, D represents the momentum term, α represents the momentum term coefficient, the value range is 0<α<1, sgn is the sign function, and λ is a constant.

[0014] Preferably, the braking distance prediction unit is used to calculate the target running speed of the elevator, including:

[0015] v t+1 =v t (1-R)

[0016] R=μ1H+μ2G

[0017] In the formula, v t represents the speed of the elevator at time t, v t+1 It represents the target operating speed of the elevator at time t+1, R represents the speed influence factor, H and G represent the environmental influence factor and load influence factor respectively, μ1 and μ2 represent the weights of the environmental influence factor and load influence factor respectively.

[0018] Preferably, the environmental impact factor is:

[0019] H=lg(σ T +σ h +σ f )

[0020]

[0021] In the formula, σ T , σ h , σ f Respectively represent the temperature influence factor, humidity influence factor and wind speed influence factor; T max , T min , They represent the maximum temperature, minimum temperature and average temperature from time t to time t+1, respectively. max 、h min , They represent the maximum humidity, minimum humidity and average humidity from time t to time t+1, respectively. max 、f min , They represent the maximum wind speed, minimum wind speed and average wind speed from time t to t+1 respectively.

[0022] Preferably, the load influencing factor is:

[0023]

[0024] In the formula, σ S , σ L They represent the uniformity influence factor and the inclination influence factor respectively, g i Indicates the material load in the i-th area of ​​the cage. There are n areas in total. Represents the average value of material load in n areas.

[0025] In a second aspect, the present invention further provides an intelligent lift for construction, comprising a control system for the intelligent lift for construction as described in any one of the above items.

[0026] In a third aspect, the present invention further provides a control method for an intelligent lift for construction, the control method comprising:

[0027] Step S10: Acquire first operation data of the elevator, the first operation data including cage load, operation speed and operation direction;

[0028] Step S20: inputting the first operation data into the trained prediction model, and outputting the braking distance of the elevator;

[0029] Step S30: obtaining the running distance between the cage floor and the target parking level in real time, and determining the size of the running distance and the braking distance;

[0030] Step S40: when the running distance is greater than the braking distance, obtaining the second running data of the elevator in real time, the second running data including environmental data, material placement uniformity and material placement inclination;

[0031] Step S50: Calculate the target operating speed of the elevator according to the second operating data, use the target operating speed to regulate the current operating speed, and update the first operating data;

[0032] Step S60: Repeat steps S20-S50 until the running distance is equal to the braking distance, and perform leveling braking control on the elevator according to the current latest braking distance.

[0033] Preferably, the prediction model is obtained by training based on BP neural network algorithm;

[0034] Among them, the momentum term is used to iteratively update the weights in the BP neural network algorithm:

[0035] w(k+1)=w(k)+η(k)[(1-α)D(k)+αD(k-1)]

[0036] η(k)=2 λη(k-1)

[0037] λ=sgn[D(k)D(k-1)]

[0038] In the formula, k represents the node of the network output layer, w represents the weight, η represents the learning rate, D represents the momentum term, α represents the momentum term coefficient, the value range is 0<α<1, sgn is the sign function, and λ is a constant.

[0039] Preferably, the target operating speed of the elevator includes:

[0040] v t+1 =v t (1-R)

[0041] R=μ1H+μ2G

[0042] In the formula, v t represents the speed of the elevator at time t, v t+1 It represents the target operating speed of the elevator at time t+1, R represents the speed influence factor, H and G represent the environmental influence factor and load influence factor respectively, μ1 and μ2 represent the weights of the environmental influence factor and load influence factor respectively.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention provides a control system for an intelligent elevator for construction, the control system comprising: an operation data acquisition unit, for acquiring first operation data of the elevator, the first operation data comprising cage load, operation speed and operation direction; a braking distance prediction unit, for inputting the first operation data into a trained prediction model, and outputting the braking distance of the elevator; acquiring the operation distance between the cage floor and the target parking level in real time, and judging the magnitude of the operation distance and the braking distance; acquiring second operation data of the elevator in real time when the operation distance is greater than the braking distance, the second operation data comprising environmental data, material uniformity and material inclination; calculating the target operation speed of the elevator according to the second operation data, regulating the current operation speed using the target operation speed, and updating the first operation data; a leveling braking control unit, for repeatedly calling the braking distance prediction unit until the operation distance is equal to the braking distance, and performing leveling braking control on the elevator according to the current latest braking distance.

[0045] The present invention first predicts the braking distance of the elevator by combining the prediction model obtained by training the neural network algorithm with the cage load, running speed and running direction. Then, the running distance between the cage floor and the target parking level is obtained in real time to determine the size of the running distance and the braking distance. When the running distance is greater than the braking distance, environmental data, material uniformity and material inclination are obtained. The environmental data include the temperature, humidity and wind speed outside the elevator cage. The running speed of the elevator is precisely regulated by environmental data, material uniformity and material inclination, which reduces the serious machine loss and even overturning of the cage caused by improper running speed, and improves the safety during operation. Then, the braking distance is also updated synchronously according to the real-time updated running speed, thereby ensuring that the floor of the cage can remain on the same plane as the plane of the target parking floor when the cage is parked, that is, accurate leveling control is achieved, which improves the safety during the construction of the elevator.

[0046] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0048] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0049] Figure 1 A schematic diagram of the structure of a control system of an intelligent lift for building construction provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the structure of a standard BP neural network model provided by an embodiment of the present invention;

[0051] Figure 3 A flow chart of a control method for an intelligent lift used in building construction provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 only 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.

[0053] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0054] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may 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. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0055] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0056] In addition, in order to better illustrate the present invention, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present invention can be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present invention.

[0057] At present, when the construction elevator is in operation, it usually relies on manual and manual experience control to stop and start, so there is often a problem that the cage cannot be leveled with the target floor after parking, which increases safety hazards. To this end, the present invention provides a control system for an intelligent elevator for construction, which can adjust the running speed in real time according to environmental factors, material uniformity and inclination, and update the predicted braking distance in real time according to the running speed, and then realize accurate leveling braking control according to the latest braking distance, which greatly improves the safety of elevator use.

[0058] See also Figure 1 , Figure 1 The present invention provides a schematic diagram of a control system for an intelligent lift used in construction. Figure 1 It can be seen that a control system for an intelligent lift used in building construction includes the following structure:

[0059] The operation data acquisition unit 100 is used to obtain first operation data of the elevator, the first operation data including cage load, operation speed and operation direction;

[0060] The braking distance prediction unit 200 is used to input the first operation data into the trained prediction model and output the braking distance of the elevator; obtain the operation distance between the cage floor and the target parking level in real time, and judge the size of the operation distance and the braking distance; when the operation distance is greater than the braking distance, obtain the second operation data of the elevator in real time, the second operation data includes environmental data, material uniformity and material inclination; calculate the target operation speed of the elevator according to the second operation data, use the target operation speed to adjust the current operation speed, and update the first operation data;

[0061] The leveling brake control unit 300 is used to repeatedly call the braking distance prediction unit until the running distance is equal to the braking distance, and then perform leveling brake control on the elevator according to the current latest braking distance.

[0062] In some embodiments, the cage load data is usually obtained by a sensor, such as a load sensor or a weighing sensor, which can monitor the weight load in the elevator cage in real time. When an object is placed in the cage, the sensor detects the change in weight and converts the change into an electrical signal, which is then transmitted to the operation data acquisition unit 100 for processing. The operating speed is usually obtained by a speed sensor, through which the operating speed of the elevator can be monitored in real time, and the data is transmitted to the operation data acquisition unit 100 for processing. The operating direction is usually divided into only up or down, and there is usually an operation interface in the elevator cage, and the current operating direction can be obtained through the indicator light or display screen of the interface.

[0063] Once the data such as cage load, running speed and running direction are obtained, they are input into the trained prediction model as the first running data, which can then quickly and accurately predict the braking distance.

[0064] In some embodiments, the prediction model is mainly obtained based on the training of the BP neural network algorithm. When training the prediction model, it is first necessary to obtain a large amount of historical operation data as a sample set, that is, the cage load, running speed and running direction generated during the historical operation process are used as input data, and the actual braking distance is used as the model output, and then the BP neural network is trained. After obtaining the training samples, in order to improve the sample quality, the samples are usually preprocessed, including data cleaning, deduplication, interpolation, etc., and finally the data is normalized to obtain sample data with better quality. Finally, the data is divided into a training set and a test set. The training set is used to train the BP neural network model, and the test set is used to detect the training results. Only when the error after training meets the requirements can the final prediction model be generated.

[0065] See also Figure 2 , Figure 2 A schematic diagram of the structure of a standard BP neural network model is provided. It should be noted that the BP neural network is based on the idea of ​​error back propagation and mainly includes three layers: input layer, hidden layer and output layer. Figure 2 As shown in Figure 1. Network transmission includes two stages, namely signal forward transmission and error reverse transmission. During the forward transmission process, the input signal passes through the hidden layer and obtains the output signal at the output layer. If the output signal is inconsistent with the expected parameters, the error begins to be transmitted backwards, and the weights and thresholds are optimized in turn through the output layer, hidden layer, and several layers to reduce the error until the set parameters are reached, that is, the training is stopped. Figure 2 In the structure, the number of neuron nodes in each layer is M, q, and L respectively. The input signal is x1, x2, …, x M , the network output signal is y1,y2,…,y L , the expected output signal is t k (k=1,2,…,L), the error signal is e k (k=1,2,…,L). Therefore, the BP neural network algorithm mainly includes the forward and reverse transmission processes of the signal. In the reverse transmission process of the error, in order to make the network converge, the weights of each layer of the network are corrected along the direction of the fastest gradient descent. Compared with other algorithms, the BP neural network has the advantages of less computational complexity, relatively simple network, and high parallelism. However, in order to further improve the learning efficiency, avoid the problem of local minimum values, and speed up the convergence speed, the BP neural network algorithm used in this embodiment is Figure 2 Improvements have been made on the basis of.

[0066] In order to effectively improve network performance and reduce network errors, in some embodiments, a momentum term is added to the standard BP algorithm to continuously correct the weights and automatically adjust the learning step size to increase the learning rate. Specifically, the momentum term is used to iteratively update the weights in the BP neural network algorithm as shown below:

[0067] w(k+1)=w(k)+η(k)[(1-α)D(k)+αD(k-1)]

[0068] η(k)=2 λ η(k-1)

[0069] λ=sgn[D(k)D(k-1)]

[0070] In the formula, k represents the node of the network output layer, w represents the weight, η represents the learning rate, D represents the momentum term, α represents the momentum term coefficient, the value range is 0<α<1, sgn is the sign function, and λ is a constant.

[0071] Therefore, the above algorithm can automatically correct the learning step size in the iterative process, so that the error function approaches the minimum point in all directions along the gradient surface with a relatively reasonable step size. During the learning process, the BP network continuously corrects the network threshold and weight in the opposite direction of the maximum error gradient change, which can minimize the network error.

[0072] Furthermore, after predicting the current braking distance of the elevator, the running distance between the cage floor and the target parking level will be obtained in real time. This distance is usually displayed in the control interface, such as using an LED display or indicator light. They will show the current position of the elevator and the target position to be parked. The running distance can be obtained by subtracting the two, and then the size of the running distance and the braking distance can be judged.

[0073] In some embodiments, when the running distance is greater than the braking distance, it proves that it is not necessary to enter the braking state now. Then the running speed should be monitored at this time. It is understandable that whether it is the external weather or the equipment itself, the loading method will affect the running speed of the elevator itself, and the environment is usually in a fluctuating state. The placement of materials will also change with the movement of the elevator. If the same running speed is always used, it may cause greater wear and tear on the machine. If the running speed does not match the loading state, in severe cases, safety accidents such as cage rollover may even occur. Therefore, in order to ensure that the running speed is in a safe state, the second running data of the elevator will be obtained at this time, and then the target running speed of the elevator will be calculated based on the second running data, and the current running speed will be regulated by using the target running speed, that is, the elevator is controlled to run at the target running speed, thereby ensuring the safety of operation. Among them, the second running data includes environmental data, material uniformity and material inclination.

[0074] In some embodiments, the braking distance prediction unit 200 is used to calculate the target running speed of the elevator, mainly using the following formula:

[0075] v t+1 =v t (1-R)

[0076] R=μ1H+μ2G

[0077] In the formula, v t represents the speed of the elevator at time t, v t+1 It represents the target operating speed of the elevator at time t+1, R represents the speed influence factor, H and G represent the environmental influence factor and load influence factor respectively, μ1 and μ2 represent the weights of the environmental influence factor and load influence factor respectively.

[0078] According to the above formula, as the environmental impact factor and load impact factor increase, the operating speed of the elevator should be reduced accordingly to improve the safety of operation.

[0079] It should be noted that the load capacity of the elevator is usually pre-set and will directly affect the operating speed of the elevator. Because as the load increases, the elevator needs more energy and time to lift the load, which leads to a decrease in operating speed. Environmental factors may also have an important impact on the operating speed of the elevator. For example, extreme temperature conditions may affect the motor efficiency and lubrication effect of the elevator, which in turn affects the operating speed. But in general, the load factor is generally considered to be a more important factor affecting the operating speed of the elevator. Therefore, regarding the size of μ1 and μ2, μ1<μ2 is usually satisfied.

[0080] Preferably, in this embodiment, μ1=0.3 and μ2=0.7 can be set, wherein the numerical value here is only an exemplary implementation. In other embodiments, the sizes of μ1 and μ2 can be determined according to different needs, and this embodiment does not impose any limitation.

[0081] In the above formula, as long as the environmental impact factor and load impact factor are obtained, the target operating speed can be quickly calculated.

[0082] In some embodiments, the environmental impact factor is:

[0083] H=lg(σ T +σ h +σ f )

[0084]

[0085] In the formula, σ T , σ h , σ f Respectively represent the temperature influence factor, humidity influence factor and wind speed influence factor; T max , T min , They represent the maximum temperature, minimum temperature and average temperature from time t to time t+1, respectively. max 、h min , They represent the maximum humidity, minimum humidity and average humidity from time t to time t+1, respectively. max 、f min , They represent the maximum wind speed, minimum wind speed and average wind speed from time t to t+1 respectively.

[0086] In this embodiment, the factors that determine the size of the environmental impact factor are mainly related to temperature, humidity and wind speed, because these three parameters will affect the operating speed of the elevator. For example, when the temperature is low, the elevator will reduce its speed due to mechanical wear, and when the wind speed is too high, the resistance received will increase, which will also reduce the operating speed of the elevator. Humidity mainly affects the elevator equipment itself. For example, when the humidity is high, the electrical components will be damp, the lubrication effect will decrease, and even mechanical thermal expansion and material corrosion problems will occur. These situations will affect the size of the operating speed. As a preferred embodiment, this embodiment mainly calculates the temperature impact factor, humidity impact factor and wind speed impact factor respectively based on the maximum value, minimum value and average value within a period of time. When the sizes of these three values ​​are obtained, the value of the environmental impact factor H can be calculated. Among them, the temperature, humidity and wind speed data can all be collected by corresponding sensors.

[0087] In some embodiments, the load influencing factor is:

[0088]

[0089] In the formula, σ S , σ L They represent the uniformity influence factor and the inclination influence factor respectively, g i Indicates the material load in the i-th area of ​​the cage. There are n areas in total. Represents the average value of material load in n areas.

[0090] In this embodiment, the load influencing factor is mainly related to the uniformity and inclination of the material placement. If the cage is divided into n areas, according to σ S The calculation formula is to first calculate the standard deviation of the difference between the load in each area and the average load, and finally calculate the ratio of the standard deviation to the average value to get the uniformity of material placement, and the inclination is to take the average of the inclination of the material in each area. The material inclination is mainly calculated by dividing the difference between the loads of two adjacent areas by the sum of the loads, thereby determining the material inclination.

[0091] When the target operating speed is calculated and used to regulate the current operating speed, precise control of the elevator operating speed can be achieved, reducing the problem of serious machine wear and tear or even cage rollover caused by improper elevator operating speed, and improving safety during operation.

[0092] Furthermore, when the target operating speed is used as the latest operating speed of the elevator, it means that the operating speed in the first operating data has also changed, so the first operating data needs to be updated at this time; after the update, the leveling braking control unit 300 will repeatedly call the braking distance prediction unit 200 until the operating distance is equal to the braking distance, and the elevator will be leveled according to the current latest braking distance, thereby ensuring that the floor of the cage can remain in the same plane with the plane of the target parking floor when it is parked, that is, precise leveling control is achieved, which improves the safety of the elevator construction process.

[0093] In summary, the control system of the intelligent elevator for construction provided by the embodiment of the present invention first predicts the braking distance of the elevator through the cage load, running speed and running direction, combined with the prediction model obtained by neural network algorithm training. Then, the running distance between the cage floor and the target parking level is obtained in real time to judge the size of the running distance and the braking distance; when the running distance is greater than the braking distance, the environmental data, material uniformity and material inclination are obtained. The environmental data includes the temperature, humidity and wind speed outside the elevator cage. The running speed of the elevator is accurately regulated by the environmental data, material uniformity and material inclination, which reduces the serious machine loss caused by improper running speed and even the problem of cage rollover, and improves the safety during operation. Then, the braking distance is also updated synchronously according to the real-time updated running speed, so as to ensure that the floor of the cage can be kept in the same plane with the plane of the target parking floor when the cage is parked, that is, accurate leveling control is achieved, and the safety of the elevator construction process is improved.

[0094] In some embodiments, the present invention further provides an intelligent lift for construction, comprising a control system for the intelligent lift for construction as described in any of the above embodiments.

[0095] See also Figure 3 In some embodiments, the present invention further provides a control method for an intelligent lift for construction, the control method comprising:

[0096] Step S10: Acquire first operation data of the elevator, the first operation data including cage load, operation speed and operation direction;

[0097] Step S20: inputting the first operation data into the trained prediction model, and outputting the braking distance of the elevator;

[0098] Step S30: obtaining the running distance between the cage floor and the target parking level in real time, and determining the size of the running distance and the braking distance;

[0099] Step S40: when the running distance is greater than the braking distance, obtaining the second running data of the elevator in real time, the second running data including environmental data, material placement uniformity and material placement inclination;

[0100] Step S50: Calculate the target operating speed of the elevator according to the second operating data, use the target operating speed to regulate the current operating speed, and update the first operating data;

[0101] Step S60: Repeat steps S20-S50 until the running distance is equal to the braking distance, and perform leveling braking control on the elevator according to the current latest braking distance.

[0102] In some embodiments, the prediction model is obtained by training based on a BP neural network algorithm;

[0103] Among them, the momentum term is used to iteratively update the weights in the BP neural network algorithm:

[0104] w(k+1)=w(k)+η(k)[(1-α)D(k)+αD(k-1)]

[0105] η(k)=2 λ η(k-1)

[0106] λ=sgn[D(k)D(k-1)]

[0107] In the formula, k represents the node of the network output layer, w represents the weight, η represents the learning rate, D represents the momentum term, α represents the momentum term coefficient, the value range is 0<α<1, sgn is the sign function, and λ is a constant.

[0108] In some embodiments, the target operating speed of the elevator includes:

[0109] v t+1 =v t (1-R)

[0110] R=μ1H+μ2G

[0111] In the formula, v t represents the speed of the elevator at time t, v t+1 It represents the target operating speed of the elevator at time t+1, R represents the speed influence factor, H and G represent the environmental influence factor and load influence factor respectively, μ1 and μ2 represent the weights of the environmental influence factor and load influence factor respectively.

[0112] In some embodiments, the environmental impact factor is:

[0113] H=lg(σ T +σ h +σ f )

[0114]

[0115] In the formula, σ T , σ h , σ f Respectively represent the temperature influence factor, humidity influence factor and wind speed influence factor; T max , T min , They represent the maximum temperature, minimum temperature and average temperature from time t to time t+1, respectively. max 、h min , They represent the maximum humidity, minimum humidity and average humidity from time t to time t+1, respectively. max 、f min , They represent the maximum wind speed, minimum wind speed and average wind speed from time t to t+1 respectively.

[0116] In some embodiments, the load influencing factor is:

[0117]

[0118] In the formula, σ S , σ L They represent the uniformity influence factor and the inclination influence factor respectively, g i Indicates the material load in the i-th area of ​​the cage. There are n areas in total. Represents the average value of material load in n areas.

[0119] It can be understood that the control method provided in this embodiment can achieve the same technical effect as the control system provided in the above embodiment. Its specific implementation can refer to the description of the above system embodiment. For the sake of brevity, it will not be repeated here.

[0120] Those skilled 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 the present invention.

[0121] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, systems and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

[0122] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0125] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable system. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0126] A person skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

Claims

1. A control system for an intelligent lift used in building construction, characterized in that: The control system comprises: An operation data acquisition unit is used to obtain first operation data of the elevator, the first operation data including cage load, operation speed and operation direction; The braking distance prediction unit is used to input the first operation data into the trained prediction model and output the braking distance of the elevator; obtain the operation distance between the cage floor and the target parking level in real time, and judge the size of the operation distance and the braking distance; when the operation distance is greater than the braking distance, obtain the second operation data of the elevator in real time, the second operation data includes environmental data, material uniformity and material inclination; calculate the target operation speed of the elevator according to the second operation data, use the target operation speed to adjust the current operation speed, and update the first operation data; The prediction model is obtained based on BP neural network algorithm training; Among them, the momentum term is used to iteratively update the weights in the BP neural network algorithm: w(k+1)=w(k)+η(k)[(1-α)D(k)+αD(k-1)] η(k)=2 λ n(k-1) λ=sgn[D(k)D(k-1)] In the formula, k represents the node of the network output layer, w represents the weight, η represents the learning rate, D represents the momentum term, α represents the momentum term coefficient, the value range is 0<α<1, sgn is the sign function, and λ is a constant; The braking distance prediction unit is used to calculate the target running speed of the elevator, including: v t+1 =v t (1-R) R=μ1H+μ2G In the formula, v t represents the speed of the elevator at time t, v t+1 represents the target operating speed of the elevator at time t+1, R represents the speed influence factor, H and G represent the environmental influence factor and the load influence factor respectively, μ1 and μ2 represent the weights of the environmental influence factor and the load influence factor respectively; The environmental impact factors are: H=lg(σ r +s h +s f ) In the formula, σ T , σ h , σ f Respectively represent the temperature influence factor, humidity influence factor and wind speed influence factor; T max , T min , They represent the maximum temperature, minimum temperature and average temperature from time t to time t+1, respectively. max 、h min , They represent the maximum humidity, minimum humidity and average humidity from time t to time t+1, respectively. max 、f min , Respectively represent the maximum wind speed, minimum wind speed and average wind speed from time t to t+1; The load influencing factor is: In the formula, σ S , σ L They represent the uniformity influence factor and the inclination influence factor respectively, g i Indicates the material load in the i-th area of ​​the cage. There are n areas in total. It represents the average value of material load in n areas; The leveling brake control unit is used to repeatedly call the braking distance prediction unit until the running distance is equal to the braking distance, and then perform leveling brake control on the elevator according to the current latest braking distance.

2. An intelligent lift for building construction, characterized in that: It comprises a control system for an intelligent lift used in building construction as claimed in claim 1.

3. A control method for an intelligent lift for construction, characterized in that: The control method comprises: Step S10: Acquire first operation data of the elevator, the first operation data including cage load, operation speed and operation direction; Step S20: inputting the first operation data into the trained prediction model, and outputting the braking distance of the elevator; The prediction model is obtained based on BP neural network algorithm training; Among them, the momentum term is used to iteratively update the weights in the BP neural network algorithm: w(k+1)=w(k)+η(k)[(1-α)D(k)+αD(k-1)] n(k)=2 λ n(k-1) λ=sgn[D(k)D(k-1)] In the formula, k represents the node of the network output layer, w represents the weight, η represents the learning rate, D represents the momentum term, α represents the momentum term coefficient, the value range is 0<α<1, sgn is the sign function, and λ is a constant; Step S30: obtaining the running distance between the cage floor and the target parking level in real time, and determining the size of the running distance and the braking distance; Step S40: when the running distance is greater than the braking distance, obtaining the second running data of the elevator in real time, the second running data including environmental data, material placement uniformity and material placement inclination; Step S50: Calculate the target operating speed of the elevator according to the second operating data, use the target operating speed to regulate the current operating speed, and update the first operating data; The target operating speed of the elevator includes: v t+1 =v t (1-R) R=μ1H+μ2G In the formula, v t represents the speed of the elevator at time t, v t+1 represents the target operating speed of the elevator at time t+1, R represents the speed influence factor, H and G represent the environmental influence factor and the load influence factor respectively, μ1 and μ2 represent the weights of the environmental influence factor and the load influence factor respectively; The environmental impact factors are: H=lg(σ T +s h +s f ) In the formula, σ T , σ h , σ f Respectively represent the temperature influence factor, humidity influence factor and wind speed influence factor; T max , T min , They represent the maximum temperature, minimum temperature and average temperature from time t to time t+1, respectively. max 、h min , They represent the maximum humidity, minimum humidity and average humidity from time t to time t+1, respectively. max 、f min , Respectively represent the maximum wind speed, minimum wind speed and average wind speed from time t to t+1; The load influencing factor is: In the formula, σ S , σ L They represent the uniformity influence factor and the inclination influence factor respectively, g i Indicates the material load in the i-th area of ​​the cage. There are n areas in total. It represents the average value of material load in n areas; Step S60: Repeat steps S20-S50 until the running distance is equal to the braking distance, and perform leveling braking control on the elevator according to the current latest braking distance.

Images