Cooperative control system for multiple cranes

Abstract

The invention discloses a cooperative control system for multiple cranes, relates to the technical field of cranes, and solves the problems that in the prior art, crane equipment operates independently, operation condition information can only be reported in a manual mode, the accuracy and timeliness are poor, and the cost is low. And accurate information cannot be provided for the user to scientifically and timely maintain the equipment. The information acquisition module is used for acquiring running state signal data when the crane works; the data classification module is used for acquiring the running state signal data cached by the control center to perform safety monitoring index AZ analysis so as to generate a processing priority table of the running state signal data, so that the data collaborative analysis efficiency is improved; the data analysis module is used for performing equipment state identification on the operation state signal data by applying a convolutional neural network algorithm and a fault diagnosis model to obtain a fault type; accurate information can be provided for a user to scientifically maintain the equipment in time, so that the cooperative control efficiency of the crane is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cranes, and in particular to a cooperative control system for multiple cranes. Background Art

[0002] Cranes are a type of lifting equipment widely used in mining, metallurgy, warehouses and other places. They play a huge role in engineering construction and other fields. They are mainly used for loading, unloading, handling and stacking containers in container railway transshipment yards and large container storage and transportation yards. As an important equipment on the construction site, the requirements for lifting technology are getting higher and higher during the operation of the equipment, and the safety protection awareness of people and equipment is constantly improving.

[0003] Since most crane equipment operates independently and cannot be integrated with the engineering construction information system, it becomes an island of engineering construction information. The equipment status and operating status information can only be reported manually, with poor accuracy and timeliness, and it is impossible to monitor and manage the construction process as a whole intuitively and vividly. At the same time, it is impossible to provide users with accurate information to scientifically and timely maintain the equipment, which can easily cause potential accidents. Based on the above shortcomings, the present invention proposes a collaborative control system for multiple cranes. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a cooperative control system for multiple cranes.

[0005] To achieve the above-mentioned object, a first aspect of the present invention provides a collaborative control system for multiple cranes, comprising an information input module, an information collection module, a data classification module, a data analysis module and an equipment maintenance module;

[0006] The information input module is connected to the control center and is used to input crane operation limit control information;

[0007] The information acquisition module includes an image acquisition unit and an operation parameter acquisition unit. The image acquisition unit is used to acquire image data when the crane is operating; the operation parameter acquisition unit is used to acquire operation timing parameters when the crane is operating; the operation timing parameters include the load voltage, load current, motor temperature, noise decibel value, load weight and moving speed of the crane at the same time;

[0008] The information collection module is used to send the collected operation status signal data to the control center in the form of a message for buffering; the operation status signal data includes image data and operation timing parameters when the crane is operating; the data classification module is used to obtain the operation status signal data buffered by the control center for safety monitoring index AZ analysis to generate a processing priority table for the operation status signal data;

[0009] The control center is used to send the operation status signal data to the data analysis module for collaborative analysis in sequence according to the processing priority table; the data analysis module is used to apply the convolutional neural network algorithm and the fault diagnosis model to the operation status signal data to identify the equipment status and obtain the fault type;

[0010] Analyze fault location information according to fault type and running sequence data; generate warning signals based on fault location information and fault type, and transmit the warning signals to the equipment maintenance module;

[0011] After receiving the early warning signal, the equipment maintenance module extracts the fault location information and the fault type, and dispatches maintenance personnel closest to the fault location to process the fault information based on the fault location information.

[0012] Furthermore, the specific analysis steps of the data classification module include:

[0013] Acquire the crane corresponding to the operation status signal data; collect the overload tonnage and overload times, working cycle times and working cycle time of the crane within a preset time period;

[0014] The total number of failures of the crane is counted as Z1; the safety monitoring index AZ of the crane is evaluated based on the total number of failures Z1, the overload tonnage and the number of overloads, the number of working cycles and the working cycle time;

[0015] The operation status signal data are arranged in descending order according to the size of the safety monitoring index AZ, and a processing priority table for the operation status signal data is generated.

[0016] Further, the operation parameter acquisition unit includes a detection sensor group arranged in the crane, and the detection sensor group includes a voltage sensor, a current sensor, a temperature sensor, a sound sensor, a load sensor and a speed sensor;

[0017] Among them, the load sensor is used to record the real-time lifting weight of the crane hook, as well as the overload tonnage and overload times of the crane hook; the number of working cycles and working cycle time of the crane are recorded by combining the lifting weight of the crane hook with the operating conditions of a single operating time period.

[0018] Furthermore, the specific analysis steps of the data analysis module include:

[0019] Extracting image data from the running status signal data, and extracting each frame of image from the image data;

[0020] A convolutional neural network algorithm is used for image recognition. Based on the pre-training of normal and abnormal states and subdivided fault types, the operating state of the crane is identified, and the identification result is fed back to the control center. The identification result includes whether the crane is normal and the corresponding fault type.

[0021] Furthermore, the data analysis module also includes:

[0022] Extract the operation timing parameters in the operation status signal data and compare them with the operation limit control information input by the information input module; if the operation timing data is within the range of the operation limit control information, it is determined that the operation status of the crane is normal, and the operation timing data of the crane is continuously monitored;

[0023] If the running status signal data exceeds the operation limit control information, the fault diagnosis model is called to perform diagnosis and analysis on the running sequence data to obtain the fault type;

[0024] Among them, the fault diagnosis model is obtained by training the LSTM neural network model based on historical data; the historical data includes historical fault data, historical abnormal data and historical fault types.

[0025] Furthermore, the load sensor also includes: if the real-time lifting weight of the crane hook exceeds a set value, an overload signal is generated to the control center.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The information collection module of the present invention is used to collect the operation status signal data of the crane during operation; the data classification module is used to obtain the operation status signal data cached by the control center to perform safety monitoring index AZ analysis, and evaluate the safety monitoring index AZ of the crane in combination with the total number of faults Z1, the overload tonnage and the number of overloads, the number of working cycles and the working cycle time to generate a processing priority table for the operation status signal data. The control center is used to send the operation status signal data to the data analysis module in sequence according to the processing priority table for collaborative analysis to improve the efficiency of data collaborative analysis;

[0028] 2. The data analysis module described in the present invention is used to apply a convolutional neural network algorithm (CNN) and a fault diagnosis model to the operating status signal data to perform equipment status identification. First, the image data in the operating status signal data is extracted, and the convolutional neural network algorithm (CNN) is applied for image recognition; based on the pre-training of normal state and abnormal state (and subdivided fault type), the operating state of the crane is identified; at the same time, the operating timing parameters in the operating status signal data are extracted. If the operating status signal data exceeds the operation limit control information, the fault diagnosis model is called to perform diagnostic analysis on the operating timing data to obtain the fault type; it can provide users with accurate information to scientifically and timely maintain the equipment, and corresponding remedial measures can be made remotely, thereby improving the efficiency of crane collaborative control. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be 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.

[0030] Figure 1 The present invention is a system block diagram of a collaborative control system for multiple cranes. DETAILED DESCRIPTION

[0031] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0032] See also Figure 1 , a first aspect of the present invention provides a collaborative control system for multiple cranes, including an information input module, a control center, an information collection module, a data classification module, a data analysis module and an equipment maintenance module;

[0033] The information input module is connected to the control center and is used to input crane operation limit control information;

[0034] The information acquisition module includes an image acquisition unit and an operation parameter acquisition unit, which are used to collect the operation status signal data of the crane during operation; wherein the operation status signal data mainly includes the image data and operation timing parameters of the crane during operation, and the operation timing parameters include the load voltage, load current, motor temperature, noise decibel value, load weight and moving speed of the crane at the same time;

[0035] In this embodiment, the image acquisition unit is used to acquire image data when the crane is operating; the operation parameter acquisition unit is used to acquire operation timing parameters when the crane is operating;

[0036] The operation parameter acquisition unit includes a detection sensor group arranged in the crane, and the detection sensor group includes a voltage sensor, a current sensor, a temperature sensor, a sound sensor, a load sensor and a speed sensor;

[0037] Among them, the load sensor is used to record the real-time lifting weight of the crane hook, as well as the overload tonnage and overload times of the crane hook; the number of working cycles and working cycle time of the crane are recorded by combining the lifting weight of the crane hook with the operating status of a single operating time period;

[0038] The present application can detect the real-time lifting weight of the crane hook in real time through the load sensor. If it exceeds the set value, an overload signal is generated to the control center to prevent the overload from affecting the balance of the crane operating room and causing the crane operating room to overturn, thereby improving work safety;

[0039] It should be noted that the information collection module is used to send the collected operation status signal data to the control center in the form of messages for caching; it should be understood that since there are multiple cranes in the construction process, the control center caches the operation status signal data of multiple cranes at the same time;

[0040] The data classification module is used to obtain the running status signal data cached by the control center to perform safety monitoring index AZ analysis to generate a processing priority table for the running status signal data; the specific analysis steps include:

[0041] Obtain the crane corresponding to the operating status signal data; collect the crane's overload tonnage and overload times, working cycle times and working cycle time within a preset time period;

[0042] The total number of crane failures is counted as Z1; the safety monitoring index AZ of the crane is evaluated based on the total number of failures Z1, overload tonnage and overload times, working cycle times and working cycle time;

[0043] Among them, the total number of failures Z1, overload tonnage and overload times, working cycle times and working cycle time are all positively correlated with the safety monitoring index AZ. The larger the safety monitoring index AZ is, the higher the possibility of abnormality of the crane is, and the more attention needs to be paid to the crane;

[0044] Arrange the operation status signal data in descending order according to the size of the safety monitoring index AZ, and generate a processing priority table for the operation status signal data; the control center is used to send the operation status signal data to the data analysis module for collaborative analysis in sequence according to the processing priority table, so as to improve the efficiency of data collaborative analysis;

[0045] In this embodiment, the data analysis module is used to apply a convolutional neural network algorithm (CNN) and a fault diagnosis model to identify the device status of the operating status signal data, specifically including:

[0046] Extracting image data from the running status signal data, and extracting each frame of image from the image data;

[0047] Apply convolutional neural network (CNN) algorithm for image recognition; based on the pre-training of normal and abnormal states (and subdivided fault types), identify the operating status of the crane and feed back the recognition results to the control center; the recognition results include whether the crane is normal and the corresponding fault type;

[0048] Extract the operation timing parameters in the operation status signal data and compare them with the operation limit control information input by the information input module; if the operation timing data is within the range of the operation limit control information, it is determined that the operation status of the crane is normal, and the operation timing data of the crane is continuously monitored;

[0049] If the operation status signal data exceeds the operation limit control information, the fault diagnosis model is called to perform diagnostic analysis on the operation sequence data to obtain the fault type; wherein the fault diagnosis model is obtained by training the LSTM neural network model based on historical data; the historical data includes historical fault data, historical abnormal data and historical fault types;

[0050] Analyze fault location information according to fault type and running sequence data; generate warning signals based on fault location information and fault type, and transmit the warning signals to the equipment maintenance module;

[0051] After receiving the warning signal, the equipment maintenance module extracts the fault location information and fault type, and dispatches the maintenance personnel closest to the fault location to handle the fault information based on the fault location information;

[0052] The present invention combines the convolutional neural network algorithm (CNN) and the fault diagnosis model to identify the equipment status (fault type) of the image data and operating sequence parameters during crane operation, which can provide users with accurate information to scientifically and timely maintain the equipment, and can also make corresponding remedial measures remotely, thereby improving the efficiency of crane collaborative control.

[0053] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0054] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A collaborative control system for multiple cranes, characterized in that: It includes information input module, information collection module, data classification module, data analysis module and equipment maintenance module; The information input module is connected to the control center and is used to input crane operation limit control information; The information acquisition module includes an image acquisition unit and an operation parameter acquisition unit. The image acquisition unit is used to acquire image data when the crane is operating; the operation parameter acquisition unit is used to acquire operation timing parameters when the crane is operating; the operation timing parameters include the load voltage, load current, motor temperature, noise decibel value, load weight and moving speed of the crane at the same time; The information collection module is used to send the collected operation status signal data to the control center in the form of a message for buffering; the operation status signal data includes image data and operation timing parameters when the crane is operating; the data classification module is used to obtain the operation status signal data buffered by the control center for safety monitoring index AZ analysis to generate a processing priority table for the operation status signal data; The control center is used to send the operation status signal data to the data analysis module for collaborative analysis in sequence according to the processing priority table; The data analysis module is used to apply the convolutional neural network algorithm and the fault diagnosis model to identify the equipment status of the operating status signal data to obtain the fault type; Analyze fault location information based on fault type and runtime data; Generate a warning signal based on the fault location information and the fault type, and transmit the warning signal to the equipment maintenance module; After receiving the early warning signal, the equipment maintenance module extracts the fault location information and the fault type, and dispatches maintenance personnel closest to the fault location to process the fault information based on the fault location information.

2. A collaborative control system for multiple cranes according to claim 1, characterized in that: The specific analysis steps of the data classification module include: Acquire the crane corresponding to the operation status signal data; collect the overload tonnage and overload times, working cycle times and working cycle time of the crane within a preset time period; The total number of failures of the crane is counted as Z1; the safety monitoring index AZ of the crane is evaluated based on the total number of failures Z1, the overload tonnage and the number of overloads, the number of working cycles and the working cycle time; The operation status signal data are arranged in descending order according to the size of the safety monitoring index AZ, and a processing priority table for the operation status signal data is generated.

3. A collaborative control system for multiple cranes according to claim 2, characterized in that: The operation parameter acquisition unit includes a detection sensor group arranged in the crane, and the detection sensor group includes a voltage sensor, a current sensor, a temperature sensor, a sound sensor, a load sensor and a speed sensor; Among them, the load sensor is used to record the real-time lifting weight of the crane hook, as well as the overload tonnage and overload times of the crane hook; the number of working cycles and working cycle time of the crane are recorded by combining the lifting weight of the crane hook with the operating conditions of a single operating time period.

4. A collaborative control system for multiple cranes according to claim 1, characterized in that: The specific analysis steps of the data analysis module include: Extracting image data from the running status signal data, and extracting each frame of image from the image data; A convolutional neural network algorithm is used for image recognition. Based on the pre-training of normal and abnormal states and subdivided fault types, the operating state of the crane is identified, and the identification result is fed back to the control center. The identification result includes whether the crane is normal and the corresponding fault type.

5. A collaborative control system for multiple cranes according to claim 4, characterized in that: The data analysis module also includes: Extract the operation timing parameters in the operation status signal data and compare them with the operation limit control information input by the information input module; if the operation timing data is within the range of the operation limit control information, it is determined that the operation status of the crane is normal, and the operation timing data of the crane is continuously monitored; If the running status signal data exceeds the operation limit control information, the fault diagnosis model is called to perform diagnosis and analysis on the running sequence data to obtain the fault type; Among them, the fault diagnosis model is obtained by training the LSTM neural network model based on historical data; the historical data includes historical fault data, historical abnormal data and historical fault types.

6. A coordinated control system for multiple cranes according to claim 3, characterized in that: The load sensor also includes: if the real-time lifting weight of the crane hook exceeds the set value, an overload signal is generated to the control center.

Images