Sensemore Maintenance Bot

Elevate your maintenance with Sensemore’s AI-powered predictive bot for increased uptime and cost savings.

In the world of industrial maintenance, keeping equipment running smoothly and efficiently is crucial for the success of any organization. But with the increasing complexity of modern machinery, it can be difficult to keep track of all the potential problems that could occur. This is where artificial intelligence (AI) comes in. Artificial intelligence has the potential to revolutionize many aspects of our lives, and one area where it is already starting to make a significant impact is in the realm of predictive maintenance.

Predictive maintenance involves using data and analytics to predict when equipment is likely to fail, so that preventive measures can be taken to avoid downtime and costly repairs.  We have already discussed the history of maintenance and answered how it has evolved to be more proactive in our other blog History and Future of Maintenance Culture – Sensemore On the other hand, today’s trend is BOTs, to be more specific AI BOTs.

An AI-powered bot, is actually a computer program that uses artificial intelligence technologies to perform specific tasks or mimic human behaviour. These tasks can include things like responding to user input, analyzing data, and making decisions. AI bots can be integrated into various applications and even today their capability is beyond human-written programs. If you do not think you have not encountered one of them, you probably have since even voice assistants in our mobile phones are also AI bots. These bots are able to generate images based on your text description, some help for coding and the most popular of all is chatGPT after its launch in December 2022. Even though they are very new in the field, they are very popular on the internet.

Going back to the original topic, the industry lacks bots when it comes to predictive maintenance. It is obvious that offline and online analysis tools provide graphical interfaces and statistical and machine learning techniques to analyze the data and make predictions. However, the outputs sometimes remain highly technical and academical for those working in the field. In order to overcome these issues, Sensemore provides an end-to-end solution from placing Sensemore sensors on your machine to its cloud platform and presents artificial intelligence analysis on collected data.

Fig.1 Sensemore Maintenance Bot Notifications

But Sensemore is more than just a predictive maintenance tool. It is also able to perform many of the tasks traditionally carried out by human maintenance workers, such as identifying and diagnosing problems, suggesting repair options, and even scheduling maintenance activities. Additionally, Sensemore’s reliability engineers communicate directly with the user to assist them about their equipments, reports and maintenance plans. This helps to reduce the workload of maintenance teams, freeing them up to focus on more complex tasks and enabling them to be more productive and efficient. For diagnose and repair options our portal sends user friendly maintenance reports that provide the root-cause of the problem. Now with the newly developed Sensemore maintenance bot, predictive maintenance is getting more effortless and uncomplicated.

Sensemore’s bot uses developed-in-house predictive maintenance algorithms such as machine mode analysis, trend type detector, faulty detector or trend predictor. This means that our bot is specifically tailored to the needs of maintenance teams and is optimized for tasks such as analyzing sensor data and predicting equipment failures almost real-time.

For example, if a piece of equipment is operating outside of its normal parameters, a bot can be configured to send a notification to a maintenance team, alerting them to the issue and providing relevant details such as the location of the machine and potential causes of the problem. In Fig.1 the bot provides notifications for the registered customers and quick look-up analysis. If further investigation is required, it directs to Sensemore cloud platform for more sophisticated tools, analysis and reports on the measurement point.

Sensemore maintenance bot is now in beta version and only available in Telegram which is a popular messaging app. Once the bot is integrated and configured, users can interact with it through Telegram’s chat interface, just as they would with any other Telegram bot. Some of the pre-defined commands can be seen in Fig.2 which helps quick reviews over mobile phones. With the help of messaging app technologies, Sensemore maintenance bot can even be send notifications over smart watches which encourages to take actions only when necessary.

Fig.2 Sensemore Maintenance Bot Available Commands

In addition to providing alerts, Sensemore bot can also be used to provide information and advice to operators and maintenance teams. For instance, the bot could be programmed to provide detailed instructions on how to perform a particular maintenance task, or to provide information about the performance and health of a particular machine. Overall, the use of bots in smart machine health platforms can greatly improve the efficiency and effectiveness of these systems. By providing real-time information and alerts, Sensemore maintenance bot can help to reduce downtime and prevent potential problems from escalating into major issues. As a result, companies that use smart machine health platforms with bots are likely to experience improved productivity and profitability.


Fault Diagnostic Technique Using AI-Assisted Machine Mode Similarity Analysis

Artificial intelligence applications are widely used for fault diagnosis by monitoring vibration data. In order for artificial intelligence applications to provide the most efficient results, they need to be trained using data obtained by regular monitoring of machines for long periods and evaluated by experts. As a result of this training, the operating characteristics of the machinery will be recognized and the diagnosis of the potential faults will be possible. However, even during the training process, machine failures must be detected successfully. In such cases, where there is not enough data readily available yet or if it is difficult to obtain working characteristics from experts, a diagnostic technique based on machine mode similarity can be used.

Raw vibration data from the sensors can be converted into meaningful features and using these features, “machine modes” that summarize the operating cycle of a machine can be found. Machine modes indicate important changes that a machine may encounter during its lifetime, such as machine downtime, minor changes in operating conditions, and malfunctions. The extracted modes indicate similar trends for similar machine types used in industry. Therefore, the operating characteristic of a machine for which there is insufficient information or measurements, can be determined using the modes of another machine whose operating characteristics are well known. A process, which could take a lot of time and effort under normal conditions, becomes easy, fast and understandable with mode similarity analysis.

Mode Similarity Analysis

For the mode similarity application, determination of a “donor” machine is the first step. A donor machine is a machine which is well recognized by our artificial intelligence algorithm and it provides the machine mode information to the system. The raw vibration data coming from the donor machine are analyzed with various techniques in time and frequency domains and decomposed into their features. These features are evaluated by the machine learning algorithm and their respective signals are separated into machine modes. The resulting modes are examined by reliability engineers who are experts in the field, in order to determine which operating conditions or fault types they belong to. Simultaneously, the data of the “acceptor” machine, are processed and its features are extracted. Acceptor machine is the machine whose status is desired to be known and to which the machine modes will be transferred. An acceptor machine should have a similar drivetrain to the donor machine. Finally, the failure modes of the acceptor machine can be determined by analyzing the similarity between the defective modes of the donor and available measurements of the acceptor machine. In this application, a real machine can be used as a donor as well as a readily available, comprehensive mode library.

Fig. 1 Mode Similarity Analysis Flow

Example Application

We can demonstrate this technique more clearly with an application. First of all, let’s consider a centrifugal pump driven by a 250 kW electric motor as the donor machine, whose operating characteristics are fully defined in our mode pool. As the acceptor machine, a fan driven by an electric motor with a capacity of 200 kW will be considered. Although the basic features of these two machines are very different, if the raw vibration data is analyzed correctly, it will be possible to transfer the machine modes by establishing a correlation between them. Both of the selected machines have variable rotational speeds. Therefore, the resonance situation, which has a critical importance in machine health, has been chosen as the type of failure to be determined in the scope of the example. However, a similar application can be applied for many other failure root causes.

The 3-axis vibration data as well as the measurement specific RPM (revolutions per minute) values were collected from the donor machine. Meaningful features were extracted from the raw data and were fed into the machine learning algorithm. The algorithm outputs the measurements divided into machine modes. The mode that shows the resonance characteristic and the measurements included in this mode were marked for comparison with the acceptor machine.

Fig. 2 3 Axis VRMS Data with Respect to Measurement Index for the Donor Machine, Separated Into Machine Modes Including the Resonance Mode

For the acceptor machine, the measurements were collected in the same way and their features were extracted. Then, as a final operation, the measurements of the mode marked as resonance failure in the donor machine and all the measurements of the acceptor machine were fed into the similarity algorithm. The resulting similarity score for each measurement indicates how close the measurement is to the resonance mode. The measurements with the highest score should then be re-examined by the reliability engineer team to fully confirm the failure mode.

In this application, the measurement number 341 has the highest similarity score and is confirmed to show the resonance characteristic for the acceptor machine.

Conclusion

Within the scope of predictive maintenance, even if a machine is still in the recognition process, its operating and failure modes can be determined by making mode similarity comparisons. In this way, it is possible to have an idea on the instant status of many machines without waiting for the initial training and estimation phases, and thus quicker reactions can be given in case of emergencies.

References:

  • Şerifoğlu, M. O., Gencer, F. B., Aktaş & A. Ö., Ulusoy, A. E. (2022). Makine Modu Benzerliğini Kullanarak Titreşim Tabanlı Rezonans Teşhisi. Uluslararası Katılımlı Bakım Teknolojileri Kongresi ve Sergisi 20-22 Ekim 2022 Denizli. ISBN: 978-605-01-1546-8