Building cooling station control method and system based on BIM

Abstract

The present invention relates to the field of air conditioning technology, and in particular to a building cold station control method and system based on BIM. The method first collects the indoor temperature and the number of people in each room; clusters the indoor temperature of each room to obtain at least two final clusters; fits the indoor temperature in each final cluster to obtain a fitting line segment and a corresponding two-dimensional vector; calculates the similarity of the two-dimensional vectors at the current moment and the previous moment as the door opening and closing evaluation value; uses the proportion of the number of people in the room as a weight, and weights the door opening and closing evaluation value to obtain a cold air loss evaluation; clusters the rooms based on the cold air loss evaluation to obtain ten categories; calculates the cold air adjustment ratio of the rooms in the category; and obtains the adjusted cold air volume from the cold air adjustment ratio. The method obtains the adjusted cold air volume by performing data analysis on the indoor temperature and the number of people in the room. Adjustment of each room is achieved to reduce the occurrence of energy waste.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning, and in particular to a building cooling station control method and system based on BIM. Background Art

[0002] A cold station can be said to be a control system. Generally speaking, a cold station is an abbreviation for a cold station group control system. Cold stations generally use centralized cold stations, and there are other forms of cold stations. Cold station technology is a green and environmentally friendly technology. It can not only greatly improve people's quality of life, but also save energy and alleviate electricity shortages. It has a very broad prospect. The purpose of regulating a building cold station is to save energy, let the cold air go where it is needed, and realize the regulation of the amount of cold air. On the basis of the low-temperature air-conditioning system to uniformly regulate the cold air in each room, there is a problem of energy waste in rooms with fewer people and fewer activities, and the users in the room can feel the loss of cold air when opening and closing the door, which makes the user experience poor.

[0003] Currently, the most common method for controlling a cold station is to collect the number of people in the space and adjust the amount of cooling air in the room based on the number of people in the space. This method only considers the number of people in the room, but does not evaluate the amount of cooling air in the room in combination with the indoor temperature and the number of people for regulation. It is not possible to adjust the amount of cooling air in the room separately according to the real-time temperature in the room. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a building cooling plant control method and system based on BIM, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a BIM-based building cooling plant control method, the method comprising the following steps:

[0006] Collect the indoor temperature and room image in each room, wherein a distributed temperature information collection method is used to monitor the temperature distribution area in each room, and a temperature sensor is installed on the ground at a position perpendicular to the center vertical line of the room door and one meter away from the center vertical line of the room door in each room, and the temperature sensor is used to collect the indoor temperature in each room;

[0007] Select any initial radius, use the DBSCAN algorithm to cluster the indoor temperature, and obtain at least two clusters; use the ratio of the median to the mean of the indoor temperature in each cluster as the clustering radius evaluation index, and continuously adjust the clustering radius. When the clustering radius evaluation index corresponding to each cluster belongs to the preset range, use the current clustering radius as the final clustering radius; based on the final clustering radius, use the DBSCAN algorithm to cluster the indoor temperature to obtain at least two final clusters;

[0008] Fitting the indoor temperature in each final cluster to obtain a fitting line segment, and converting the fitting line segment into a corresponding two-dimensional vector; calculating the similarity of the two-dimensional vector corresponding to the current moment and the previous moment as the evaluation value of the door opening and closing;

[0009] The number of people in the room is obtained according to the room image, and the proportion of the number of people in each room is used as a weight to weight the door opening and closing evaluation value to obtain a cold air loss evaluation; the rooms are clustered based on the cold air loss evaluation to obtain ten categories; a histogram is made based on the number of rooms in each category and the corresponding cold air loss evaluation, and the proportion of the area corresponding to each category in the histogram is used as the cold air adjustment ratio of the room in the category; the cold air adjustment ratio is multiplied by the current cold air amount equipped in each room to obtain the adjusted cold air amount.

[0010] Preferably, fitting the indoor temperature in each final cluster to obtain a fitting line segment, and converting the fitting line segment into a corresponding two-dimensional vector includes:

[0011] The indoor temperature in each final cluster is fitted with a straight line to obtain a fitting straight line; the fitting straight line is intercepted according to the maximum and minimum values ​​of the indoor temperature corresponding to each final cluster, the projection point of the minimum value of the indoor temperature on the fitting straight line is used as the starting point of the fitting line segment, and the projection point of the maximum value of the indoor temperature on the fitting straight line is used as the end point of the fitting line segment to obtain the fitting line segment;

[0012] The length of the fitted line segment is taken as the length of the two-dimensional vector, and the direction from the start point to the end point of the fitted line segment is taken as the direction of the two-dimensional vector, so as to obtain the two-dimensional vector corresponding to the fitted line segment.

[0013] Preferably, the method for obtaining the door opening and closing evaluation value is:

[0014] The cosine similarity between the two-dimensional vector corresponding to the current moment and the two-dimensional vector corresponding to the previous moment is calculated as the evaluation value of the door opening and closing of the room.

[0015] Preferably, the method for obtaining the number of people in the room is:

[0016] Perform head detection on the room image to obtain the number of people in the room.

[0017] Preferably, the making of a histogram based on the number of rooms in each category and the corresponding cold air loss evaluation comprises:

[0018] The horizontal axis of the histogram is the cold air loss evaluation corresponding to the indoor temperature in each category, and each category has its own corresponding cold air loss evaluation range; the vertical axis is the number of rooms in each category, where the cold air loss evaluation range is the range between the minimum cold air loss evaluation and the maximum cold air loss evaluation corresponding to the rooms in the category, and the cold air loss evaluation range includes the minimum cold air loss evaluation and the maximum cold air loss evaluation in the category.

[0019] Preferably, the area corresponding to each category in the histogram is: the product of the length of the cold air loss evaluation range corresponding to each category and the number of rooms in the category.

[0020] In a second aspect, an embodiment of the present invention provides a BIM-based building refrigeration plant control system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned BIM-based building refrigeration plant control method when executing the computer program.

[0021] The embodiments of the present invention have at least the following beneficial effects:

[0022] The method first collects the indoor temperature and room image in each room; clusters the indoor temperature corresponding to each room to obtain at least two final clusters. Fits the indoor temperature in each final cluster to obtain a fitting line segment, and converts the fitting line segment into a corresponding two-dimensional vector; calculates the similarity of the two-dimensional vector corresponding to the current moment and the previous moment as the door opening and closing evaluation value; clusters the indoor temperature corresponding to the room, and calculates the similarity of the indoor temperature at the current moment and the adjacent moment as the door opening and closing evaluation, so as to evaluate the door opening and closing in the room, which will affect the loss of cold air in the room.

[0023] The number of people in the room is obtained according to the room image, and the proportion of the number of people in each room is used as a weight to weight the door opening and closing evaluation value to obtain the cold air loss evaluation; because the number of people in the room will also affect the loss of cold air in the room, the number of people is used as a weight to weight the door opening and closing evaluation value.

[0024] Based on the cold air loss evaluation, the rooms are clustered into ten categories; a histogram is drawn based on the number of rooms in each category and the corresponding cold air loss evaluation, and the proportion of the area corresponding to each category in the histogram is used as the cold air adjustment ratio of the room in the category; the adjusted cold air volume is obtained by multiplying the cold air adjustment ratio by the current cold air volume of each room. Based on the cold air loss evaluation, the rooms are clustered into ten categories to facilitate the subsequent regulation of the cold air volume, which realizes different regulation of different rooms and avoids the complexity of the calculation of cold air volume regulation for each room. This method obtains the corresponding cold air adjustment ratio for each room by performing data analysis on the indoor temperature and the number of people in the room. Separate regulation of each room is achieved to reduce energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 A method flow chart of a BIM-based building cooling plant control method provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the BIM-based building cooling station control method and system proposed by the present invention, its specific implementation, structure, features and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0028] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0029] The embodiment of the present invention provides a specific implementation method of a building cooling station control method and system based on BIM, and the method is applicable to the building cooling station control scenario. In this scenario, the building cooling station controls the cooling volume of multiple rooms, each room is equipped with a temperature sensor for collecting the indoor temperature in the room, and a camera is also installed for obtaining the room image. In order to solve the problem of regulating the cooling volume in the room according to the number of people in the space, the method only considers the number of people in the room, and does not evaluate the cooling volume in the room in combination with the indoor temperature and the number of people for regulation. The present invention classifies the rooms according to the indoor temperature in the room, calculates the door opening and closing evaluation value of each room, and then obtains the cooling loss evaluation of the room in combination with the number of people in the room, performs data processing on the cooling loss evaluation to obtain the corresponding cooling adjustment ratio, and adjusts the cooling volume equipped in each room according to the cooling adjustment ratio to obtain the adjusted cooling volume. The method obtains the cooling adjustment ratio corresponding to each room by performing data analysis on the indoor temperature and the number of people in the room. It realizes the separate adjustment of each room to reduce the occurrence of energy waste.

[0030] The specific scheme of the BIM-based building cooling station control method and system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0031] See also Figure 1 , which shows a method flow chart of a BIM-based building cooling station control method provided by an embodiment of the present invention, the method comprising the following steps:

[0032] Step S100, collecting the indoor temperature and room image of each room.

[0033] Firstly, a distributed temperature information collection method is used to monitor the temperature distribution area in each room. A temperature sensor is installed on the ground at a position perpendicular to the center vertical line of the room door and one meter away from the center vertical line of the room door in each room. The temperature sensor is used to collect the indoor temperature in each room.

[0034] The speed of temperature change in the space indicates the actual temperature increase speed. That is, the temperature increase speed is affected by the temperature difference between the inside and outside, and the greater the temperature difference, the faster the change speed. Therefore, in the area where the temperature overflows, such as the door, which is sensitive to the indoor temperature, the temperature loss at each location can be expressed by the temperature change in the actual detection to calculate the overall loss. The acquisition frequency of the temperature sensor is 50Hz.

[0035] A camera is installed in the room to collect video in the room, and the video is framed to obtain a room image. Head detection is performed on the obtained room image to obtain the number of people in the room. It should be noted that head detection is a well-known technology for those skilled in the art and will not be described in detail here.

[0036] Step S200, select any initial radius, use the DBSCAN algorithm to cluster the indoor temperature, and obtain at least two clusters; use the ratio of the median to the mean of the indoor temperature in each cluster as the clustering radius evaluation index, and continuously adjust the clustering radius. When the clustering radius evaluation index corresponding to each cluster is within a preset range, use the current clustering radius as the final clustering radius; based on the final clustering radius, use the DBSCAN algorithm to cluster the indoor temperature to obtain at least two final clusters.

[0037] Determine the temperature change boundary of each room, taking the door of any room as an example. Since the room changes to the outside temperature through heat conduction via temperature difference, in actual monitoring, the room temperature will be affected by the user opening and closing the door, and there will be a large impact. Therefore, it is necessary to analyze the impact of the temperature change in the room, and monitor the area where the temperature changes more quickly. When someone uses the room door, that is, when the room door is opened and closed, the opening of the door will cause a short-term drastic change in temperature, which is the starting point for adjustment.

[0038] First, the DBSCAN algorithm is used to screen the indoor temperature data of each room to determine the interval of opening and closing the room door. That is, when the room door is opened and closed, it is considered that the temperature changes more dramatically at this stage. Therefore, the DBSCAN algorithm can be used to find clusters in continuous time. When obvious data stratification appears, the next cluster appears, that is, the degree to which the room door is open or closed at this time.

[0039] Select an arbitrary initial radius r, and the radius r needs to be corrected later. Based on the initial radius r, the DBSCAN algorithm is used to cluster the multiple indoor temperatures corresponding to each room to obtain at least two clusters. The number of indoor temperatures in each cluster is not less than two. It should be noted that since the indoor temperature is constantly obtained, each room has multiple corresponding indoor temperatures. The several clusters obtained can express the opening state of the room door at this time, and the specific evaluation value of the door opening and closing can be obtained by using the difference in clusters. The loss of calculating clustering is that due to the uncertainty of the data, the ratio of the median to the mean of the indoor temperature in each cluster is used as the clustering radius evaluation index. When the ratio is closer to 1, the more accurate the classification result is.

[0040] The clustering radius is continuously adjusted, and a new cluster is obtained after adjusting the clustering radius. When the clustering radius evaluation index corresponding to each cluster is within the preset range, the clustering radius of the current cluster is used as the final clustering radius. In the embodiment of the present invention, the preset range is [0.7, 1.3]. In other embodiments, the implementer can adjust the range according to the actual situation. The preset range is an acceptable data fluctuation range. When the obtained clustering accuracy evaluation data is within the preset range, it means that the classification result of the cluster obtained by clustering at this time is more accurate. If the clustering radius evaluation index exceeds 1.3, the clustering radius r should be appropriately reduced; conversely, if the clustering radius evaluation index is less than 0.7, it is necessary to appropriately expand the clustering radius. Until the clustering accuracy evaluation index can fall within the threshold range of [0.7, 1.3], it is considered that a more appropriate clustering radius is obtained.

[0041] Based on the final clustering radius, the DBSCAN algorithm is used to cluster the indoor temperature to obtain at least two final clusters.

[0042] Step S300, fitting the indoor temperature in each final cluster to obtain a fitting line segment, and converting the fitting line segment into a corresponding two-dimensional vector; calculating the similarity of the two-dimensional vector corresponding to the current moment and the previous moment as the door opening and closing evaluation value.

[0043] Furthermore, the evaluation of the change in the opening and closing state of the room door is calculated, because the opening and closing of the room door will affect the change in temperature.

[0044] First, the temperature data in each final cluster is linearly analyzed, that is, the indoor temperature in each final cluster is fitted to obtain fitting segments, and the fitting segments are converted into corresponding two-dimensional vectors. Since the temperature data changes are small under the premise that the temperature difference is small and the degree of door opening and closing is different, the data changes in each final cluster are difficult to change significantly in a short time. Therefore, when fitting the indoor temperature in each final cluster to obtain fitting segments, the indoor temperature collection time is set to collect once every two seconds. The reason for setting it to collect once twice is that the temperature will change significantly only after more than two seconds; that is, when the room door is opened and closed within two seconds, the change in the indoor temperature is low and can be ignored. And the temperature that is not collected within two seconds can be quickly supplemented at the original temperature, and there is no large perception gap in actual human perception.

[0045] Therefore, the indoor temperature data in each final cluster is fitted with a least square method to obtain a fitting line segment, and the fitting line segment is converted into a corresponding two-dimensional vector, where the loss function loss uses the mean square error loss function, and the loss function loss is required to be close to 0. Get the fitting line segment and the corresponding two-dimensional vector Specifically: Fit the indoor temperature in each final cluster to get a fitting line; intercept the fitting line according to the maximum and minimum values ​​of the indoor temperature corresponding to each final cluster, and take the projection point of the minimum value of the indoor temperature on the fitting line as the starting point of the fitting line segment, and take the projection point of the maximum value of the indoor temperature on the fitting line as the end point of the fitting line segment to get the fitting line segment; take the length of the fitting line segment as the length of the two-dimensional vector, and take the direction from the starting point to the end point of the fitting line segment as the direction of the two-dimensional vector, and get the two-dimensional vector corresponding to the fitting line segment. It should be noted that since the indoor temperature data of each room is continuously collected over time, the corresponding two-dimensional vector is also continuously updated. Among them, the two-dimensional vector is a vector containing length and direction. The direction can express the change of temperature data. The two-dimensional vector corresponding to the jth group of final clusters is recorded as .

[0046] Furthermore, the similarity of the two-dimensional vectors corresponding to the current moment and the previous moment is calculated as the door opening and closing evaluation value. The purpose of calculating the similarity of the two-dimensional vectors corresponding to the current moment and the previous moment as the door opening and closing evaluation value is to determine whether the room door has been opened or closed by comparing the similarity of the two-dimensional vectors. The method for obtaining the door opening and closing evaluation value is specific: the cosine similarity of the two-dimensional vector corresponding to the current moment and the two-dimensional vector corresponding to the previous moment is calculated as the room door opening and closing evaluation value.

[0047] The calculation formula for the door opening and closing evaluation value is:

[0048]

[0049] in, is the door opening and closing evaluation value corresponding to the i-th final cluster; is the cosine similarity function; is the two-dimensional vector corresponding to the j-1th moment; is the two-dimensional vector corresponding to the j-th moment.

[0050] The temperature change data within the first two seconds of clustering the final cluster corresponding to the calculation of cosine similarity is clustered. When the door opening and closing evaluation value approaches 1, it means that the indoor temperature data of the two final clusters have a high degree of similarity in change, indicating that the degree of opening and closing of the room door has decreased. When the door opening and closing evaluation value approaches -1, it means that the two sets of temperature data have opposite changes, indicating that the degree of opening and closing of the room door has increased. The door opening and closing evaluation value corresponding to the i-th final cluster is the i-th change in the opening and closing of the room door. Using temperature to characterize the degree of opening and closing of the room door means that the opening and closing state of the room door can be judged based on the temperature, and on the basis of considering the external temperature difference on the indoor and outdoor heat exchange efficiency, the calculation takes into account similar clusters, that is, similar opening and closing states. If no clustering occurs at this time, the evaluation data of the change in the opening and closing state of the room door of the room is supplemented with 0.

[0051] Based on the overall room door opening and closing status evaluation at the same time, the overall room door opening and closing status evaluation set of all rooms is obtained by analogy: Where n is the number of rooms, and hdoor means the entire room.

[0052] Step S400, obtaining the number of people in the room according to the room image, taking the proportion of the number of people in each room as a weight, weighting the door opening and closing evaluation value, and obtaining a cold air loss evaluation; clustering each room based on the cold air loss evaluation to obtain ten categories; making a histogram based on the number of rooms in each category and the corresponding cold air loss evaluation, and taking the proportion of the area corresponding to each category in the histogram as the cold air adjustment ratio of the room in the category; and multiplying the cold air adjustment ratio by the current cold air amount of each room to obtain the adjusted cold air amount.

[0053] In addition to the door opening and closing factor, there is also the heat dissipation property of people in the room, which causes the local temperature in the room to rise. Under the same conditions, the indoor temperature of a room with more people is higher than that of a room with fewer people. When the number of people is large enough, the above adjustment of the indoor temperature lacks rationality. Therefore, further, according to the size of the flow of people in the room, that is, the number of people in the room, the door opening and closing evaluation value is weighted.

[0054] Get the number of people in the room based on the room image. Specifically: perform head detection on the room image to get the number of people in the room. Make a weight bias for the amount of supplementary cooling air in each room based on the number of people in the room, and set the number correction bias.

[0055] The ratio of the number of people in each room is used as a weight, that is, the ratio of the number of people in each room to the total number of people in all rooms is used as the ratio of the heat dissipated by the human body, and is added to the room opening and closing evaluation value obtained in step S300. The ratio is used as a weight to weight the door opening and closing evaluation value to obtain a new value as the cold air loss evaluation in the room; that is, the ratio of the number of people in each room is used as a weight to weight the room opening and closing evaluation value to obtain the cold air loss evaluation. The cold air loss evaluation is jointly determined by the opening and closing of the room door and the number of people in the room. Because the opening and closing of the room door is one of the main ways of cold air loss, but due to the large number of people in the room, the heat in the room will increase, and the room temperature will continue to rise by radiation, evaporation, convection, conduction, etc.

[0056] Based on the obtained cold air loss evaluation, each room is clustered to obtain ten categories. In the embodiment of the present invention, the method for clustering each room based on the cold air loss evaluation is a k-means algorithm. Among them, the radial function uses the Euler function to calculate the corresponding ten clustering results, that is, to obtain ten categories. The data within the ten categories are sorted in order of size to determine the cold air loss evaluation interval within the cluster. Among them, the negative interval indicates that the room door opening and closing becomes smaller, and conversely, the positive interval indicates that the room door opening and closing becomes larger. Because the door opening and closing evaluation value may be positive or negative, the corresponding weighted cold air loss evaluation also has positive and negative numbers. The cold air loss evaluation interval containing negative numbers is used as a negative interval, indicating that the room door opening and closing degree changes from large to small, and the cold air loss amount is small; the cold air loss evaluation interval that is all positive numbers is used as a positive interval, indicating that the door opening and closing degree changes from large to small, and the cold air loss amount is large.

[0057] A histogram is drawn based on the number of rooms in each analogy and the corresponding cold air loss evaluation, that is, a histogram is drawn based on the ten categories obtained. The horizontal axis interval of each unit is the size interval of the data within each category, and the vertical axis is the number in each interval. That is, the horizontal axis of the histogram is the cold air loss evaluation corresponding to the indoor temperature in each category, and each category has its own corresponding cold air loss evaluation range; the vertical axis is the number of rooms in each category, where the cold air loss evaluation range is the range between the minimum cold air loss evaluation and the maximum cold air loss evaluation corresponding to the rooms in the category, and the cold air loss evaluation range includes the minimum cold air loss evaluation and the maximum cold air loss evaluation in the category.

[0058] Furthermore, the area of ​​each unit is calculated, that is, the area obtained by multiplying the length of the interval within each category by the number; that is, the area corresponding to each category is calculated, that is, the product of the length of the cold air loss evaluation range corresponding to each category and the number of rooms in the category.

[0059] And calculate the proportion of the area size corresponding to each category to the total area, that is, the proportion of the area corresponding to each category. The proportion of the area corresponding to each category in the histogram is used as the air conditioning adjustment ratio of the room in the category. Among them, the negative interval is to reduce the amount of air conditioning in the room according to the air conditioning adjustment ratio, and the positive interval is to increase the amount of air conditioning in the room according to the air conditioning adjustment ratio. In this way, both the degree of opening and closing of the doors of each room in the whole can be taken into account, and the influence of the people in the room on the adjustment of the air conditioning volume can also be taken into account.

[0060] The adjusted cooling volume is obtained by multiplying the cooling adjustment ratio by the current cooling volume of each room. The above method can make corresponding adjustments to the cooling of the cold station, distribute the cooling to the corresponding position at the appropriate time according to the weight, and adjust the overall weight at the cold station terminal according to the existing room cooling volume. This adjustment can greatly reduce the energy waste in rooms with fewer people, and can also ensure that it can adjust and replenish the cooling air in time on the basis of a large amount of cooling air loss caused by opening and closing the door. The result of this adjustment is that the user will not feel the obvious change of indoor temperature on the basis of timely replenishment when opening and closing the door. Among them, the stop of cooling air replenishment is determined by the air conditioning temperature, that is, the replenishment will stop immediately when the real-time temperature of the sensor reaches the air conditioning set temperature.

[0061] The present invention uses temperature as the basis to judge the opening and closing of the room door. When someone enters the room, the interval between opening and closing the door will cause the value of the door temperature sensor to change. The state of opening and closing the doors of all rooms is further judged and regulated. Based on the state of the room door opening and closing and the number of people in the room, real-time global cooling is adjusted in real time. When the door is opened to a large extent, the cold air in the room is lost too quickly. Even if the cold air supply is adjusted globally, the optimal distribution is achieved without increasing energy supplementation, so that people in the room will not feel the large temperature difference caused by frequent opening and closing of the door.

[0062] In summary, the present invention relates to the field of data processing technology. The method first collects the indoor temperature and room image in each room; selects an arbitrary initial radius, and uses the DBSCAN algorithm to cluster the indoor temperature to obtain at least two clusters; uses the ratio of the median to the mean of the indoor temperature in each cluster as a clustering radius evaluation index, and continuously adjusts the clustering radius. When the clustering radius evaluation index corresponding to each cluster is within a preset range, the current clustering radius is used as the final clustering radius; based on the final clustering radius, the DBSCAN algorithm is used to cluster the indoor temperature to obtain at least two final clusters; fits the indoor temperature in each final cluster to obtain a fitting line segment, and converts the fitting line segment into is the corresponding two-dimensional vector; calculate the similarity of the two-dimensional vector corresponding to the current moment and the previous moment as the door opening and closing evaluation value; obtain the number of people in the room according to the room image, take the proportion of the number of people in each room as the weight, weight the door opening and closing evaluation value, and obtain the cold air loss evaluation; cluster each room based on the cold air loss evaluation to obtain ten categories; make a histogram based on the number of rooms in each category and the corresponding cold air loss evaluation, and take the proportion of the area corresponding to each category in the histogram as the cold air adjustment ratio of the room in the category; multiply the cold air adjustment ratio by the current cold air volume of each room to obtain the adjusted cold air volume. This method obtains the corresponding cold air adjustment ratio for each room by performing data analysis on the indoor temperature and the number of people in the room. It realizes the separate adjustment of each room to reduce the occurrence of energy waste.

[0063] The embodiment of the present invention further proposes a BIM-based building refrigeration plant control system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program. Since the BIM-based building refrigeration plant control method has been described in detail above, it will not be repeated here.

[0064] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A building cooling station control method based on BIM, characterized in that: The method comprises the following steps: Collect the indoor temperature and room image in each room, wherein a distributed temperature information collection method is used to monitor the temperature distribution area in each room, and a temperature sensor is installed on the ground at a position perpendicular to the center vertical line of the room door and one meter away from the center vertical line of the room door in each room, and the temperature sensor is used to collect the indoor temperature in each room; Select any initial radius, use the DBSCAN algorithm to cluster the indoor temperature, and obtain at least two clusters; use the ratio of the median to the mean of the indoor temperature in each cluster as the clustering radius evaluation index, and continuously adjust the clustering radius. When the clustering radius evaluation index corresponding to each cluster belongs to the preset range, use the current clustering radius as the final clustering radius; based on the final clustering radius, use the DBSCAN algorithm to cluster the indoor temperature to obtain at least two final clusters; Fitting the indoor temperature in each final cluster to obtain a fitting line segment, and converting the fitting line segment into a corresponding two-dimensional vector; calculating the similarity of the two-dimensional vector corresponding to the current moment and the previous moment as the evaluation value of the door opening and closing; The number of people in the room is obtained according to the room image, and the proportion of the number of people in each room is used as a weight to weight the door opening and closing evaluation value to obtain a cold air loss evaluation; the rooms are clustered based on the cold air loss evaluation to obtain ten categories; a histogram is made based on the number of rooms in each category and the corresponding cold air loss evaluation, and the proportion of the area corresponding to each category in the histogram is used as the cold air adjustment ratio of the room in the category; the cold air adjustment ratio is multiplied by the current cold air amount equipped in each room to obtain the adjusted cold air amount.

2. The BIM-based building cooling plant control method according to claim 1, characterized in that: The indoor temperature in each final cluster is fitted to obtain a fitting line segment, and the fitting line segment is converted into a corresponding two-dimensional vector, including: The indoor temperature in each final cluster is fitted with a straight line to obtain a fitting straight line; the fitting straight line is intercepted according to the maximum and minimum values ​​of the indoor temperature corresponding to each final cluster, the projection point of the minimum value of the indoor temperature on the fitting straight line is used as the starting point of the fitting line segment, and the projection point of the maximum value of the indoor temperature on the fitting straight line is used as the end point of the fitting line segment to obtain the fitting line segment; The length of the fitted line segment is taken as the length of the two-dimensional vector, and the direction from the start point to the end point of the fitted line segment is taken as the direction of the two-dimensional vector, so as to obtain the two-dimensional vector corresponding to the fitted line segment.

3. The BIM-based building cooling plant control method according to claim 1, characterized in that: The method for obtaining the door opening and closing evaluation value is as follows: The cosine similarity between the two-dimensional vector corresponding to the current moment and the two-dimensional vector corresponding to the previous moment is calculated as the evaluation value of the door opening and closing of the room.

4. The BIM-based building cooling plant control method according to claim 1, characterized in that: The method for obtaining the number of people in the room is: Perform head detection on the room image to obtain the number of people in the room.

5. The BIM-based building cooling plant control method according to claim 1, characterized in that: The histogram based on the number of rooms in each category and the corresponding cold air loss evaluation includes: The horizontal axis of the histogram is the cold air loss evaluation corresponding to the indoor temperature in each category, and each category has its own corresponding cold air loss evaluation range; the vertical axis is the number of rooms in each category, where the cold air loss evaluation range is the range between the minimum cold air loss evaluation and the maximum cold air loss evaluation corresponding to the rooms in the category, and the cold air loss evaluation range includes the minimum cold air loss evaluation and the maximum cold air loss evaluation in the category.

6. The BIM-based building cooling plant control method according to claim 5, characterized in that: The area corresponding to each category in the histogram is: the product of the length of the cold air loss evaluation range corresponding to each category and the number of rooms in the category.

7. A BIM-based building refrigeration plant control system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images