Half-day seminar Digital Retrofit 4.0

Half-day seminar «Digital Retrofit 4.0» – How to make your plant fit for the digital future



The experts LeanBI, SICK, Brütsch & Rüegger and GradeSens will work out the positive effects of digital retrofits with you in an interactive dialogue in several small groups.


Industrie 2025, Swissmem and the Data Innovation alliance cordially invite you. The seminar will take place at Swissmem in Zurich on 24.11.2022 from 13:00 – 17:30, starting at 17:30 apero and closing.


Program and registration

Edge computing is often the better choice for predictive quality

LeanBI in the media on the topic:


Quality is one of the most important factors in production. For this reason, many companies rely on predictive quality applications that permanently optimize the quality of products and processes. Often, this is done via the cloud, but especially when things have to move quickly, it pays to rely on edge computing. We show what companies need to pay attention to and how they can optimize machine learning models so that they can be used on edge systems.




www.it-daily.net: Bei Predictive Quality ist Edge Computing oft die bessere Wahl


www.it-production.com: Predictive Quality: Was, wenn es schnell gehen muss


www.i40-magazin.de: Was, wenn es schnell gehen muss?


www.service-and-maintenance.com: Predictive Quality: Was, wenn es schnell gehen muss


www.itiko.de: Bei Predictive Quality ist Edge Computing oft die bessere Wahl


www.iavcworld.de: Bei Predictive Quality ist Edge Computing oft die bessere Wahl


Indoor air quality: Five reasons for more transparency

LeanBI in the media on the topic:


Not only since Corona have companies and organizations been concerned about the air quality in rooms. Only when the air quality is right can employees be efficient, energy costs optimized and office and conference rooms optimally utilized. But how can air quality actually be measured? We show what positive effects can be achieved.




Management und Qualität: Indoor air quality: Five reasons for more transparency


Organisator: Indoor air quality: Five reasons for more transparency


www.maschinenmarkt.de: Fünf gute Gründe für eine smarte Sicherung der Luftqualität

When drones inspect bridges

LeanBI in the media on the topic:


Detecting damage to infrastructures such as bridges, tunnels or canals in the conventional way is time-consuming, expensive and even dangerous. When experts inspect bridges or tunnels on site, they have to be closed off. Inspectors can only get to bridges with lifting platforms or by abseiling, which entails a risk to life and limb.



bigdata-insider.de: Whether bridges, tunnels or canals: Data analytics solutions can automate infrastructure damage detection.


Damage detection in sewerage systems

Automated detection of damages and objects in sewerage systems with artificial intelligence


Fig.1: Automatically detected deposits at the bottom in a sewerage system (image unwinding of the sewerage system).


Optimizing and increasing the efficiency of sewerage system inspection and revision is an important topic for our society. The engineering company Basler & Hofmann AG has taken up the challenge in cooperation with LeanBI AG.


And to anticipate the conclusion of the article: Artificial intelligence (AI) massively increases efficiency, but engineers and experts still don’t have to be cut back. AI helps the experts to perform their work better, which is accompanied by a high cost-saving potential. But more on that later.


The total length of public and private sewerage systems in Switzerland is over 100,000 km. According to “Die Volkswirtschaft” [1], the replacement value is estimated at a total of 114 billion CHF. In principle, the average service life of sewerage pipelines of about 70 years is high [2]. But experts assume an increased need for investment, since many pipelines were built in the 60’s to 80’s. According to “Die Volkswirtschaft” [1], the total value maintenance costs over the next 30 years will be around 130 billion Swiss francs. This means that we will have average annual maintenance costs of 4.3 billion CHF. According to [3], the value maintenance of the sewerage network is currently between 50 and 400 CHF per year and inhabitant and thus shows a high range. With a population of 8.7 million inhabitants in Switzerland, this figure indeed indicates that the total value maintenance will be accompanied by a strong cost increase in the coming years.


At a minimum, public sewerage systems should be inspected every 10 to 15 years to determine their condition. Allegedly, studies show that about 20% of sewerages are renewed unnecessarily and 15% are not rehabilitated in time. We estimate that a qualitative improvement of the current monitoring of sewerages would save 10% of the CHF 4.3 billion, i.e., savings of CHF 430 million per year in Switzerland on average over the next 30 years. We are convinced that these savings are achievable, as shown in the following.


Two system principles are in use today for sewerage inspections:


  • Conventional video cameras that can be panned by the camera operator when damage is suspected. The damage is then documented directly by the operator in software.




Fig. 2: Example iPEK Special TV, carriage for pipe diameters 250 – 1000 mm from Wikipedia


  • PANO-scan technology with two fisheye cameras that shoot an image every 5 cm, from which a 3D image can be generated along the sewerage.




Fig. 3: Example IBAK PANORAMO 4K, camera system / 3D scanner, application range from DN 200


Most public sewerages have diameters between DN 200 and DN 1800, where the PANO-scan technology can be used.  The advantage of the PANO-scan technology is that the damage inspection can be carried out not on site, but afterwards on a “digital twin”, a 3D panoramic image of the sewerage system. In addition to the improved inspection process, this technology provides a digitized and traceable database for future redevelopment.


PANO-scan recording on site in the sewerage takes place without stops and is accordingly recorded quickly and can be planned well in advance. The error rate of damage detection is reduced compared to conventional technology, as a trained expert does not perform the inspection on site, but afterwards on the computer. Various software solutions are available today for this purpose. The KINS solution from the company Kanalinformatik GmbH, which was also used in this project, is widely used in Switzerland.


Despite the great progress of PANO-Scan technology, it remains a feat to inspect the many sewerage kilometers (estimated 7,000 km/year) manually at the office workstation. The inspection takes place in a combination directly on the 3D image and the unwinding of the sewerage system. In the 3D image, the perspective can be freely selected, so that even difficult objects such as root inclusions can be better identified. Despite new camera technology, the quality of the inspection is and remains a question of the experience and concentration of the expert employed. In addition to the manual effort, the evaluation and classification of the damage allows for a great deal of subjective freedom, making the recognition of condition and damage dependent on the analyzing expert. We were also able to determine such subjectivity in our statistical evaluations of various municipalities.


Automated evaluation of the recorded data material, on the other hand, leads to improved and consistent monitoring quality by minimizing errors due to fatigue, ignorance (insufficient training) or overlooking of damage. In other words, subjectivity is largely eliminated.


In 2020, Basler & Hofmann AG commissioned LeanBI AG to develop machine learning models for the automated detection of damage and contamination in sewerages. Today, such models are also referred to as artificial intelligence.




As an internationally active engineering firm headquartered in Switzerland, Basler & Hofmann AG provides services for the planning and maintenance, in particular condition surveys and inspections, of infrastructure structures and is familiar with the needs and requirements of sewerage operators. Basler & Hofmann uses its own engineers to evaluate the damage in the sewerage systems.


For the project, a team of Basler & Hofmann engineers, LeanBI data scientists and subject matter experts was formed to drive the automation of damage detection. Large amounts of image material from large and small rural communities, as well as cities, were statistically analyzed. The approximately 200 damage categories of the VSA (Verband Schweizer Abwasser- und Gewässerschutzfachleute) guideline were clustered in such a way that in the future 95% of damage cases and pollution can be detected automatically with artificial intelligence.


Fig. 4 shows a schematic representation of the manual annotation process of damaged lateral connections: The relevant markings are marked on the images with pixel precision using an annotation tool. These markings are then exported and combined into binary masks on a class-by-class basis. Together with the unwinding images, these masks form the basis for the training data.



Fig. 4: Manual annotation process in the unwinding of a sewerage pipe


The machine learning models were then trained based on the manual annotations. In contrast to existing solutions, the project team decided to apply the so-called “machine learning image segmentation”, i.e., a pixel-precise defect detection of the object or damage. The machine learning models thus detect the exact shape of the defects, in contrast to the few solutions available on the market today, which usually place “bounding boxes” around the objects. Let us illustrate the segmentation with an example based on an incompletely bound connection shown in Fig. 5.




Fig. 5: Image of a lateral connection “incompletely integrated


In the automated detection with artificial intelligence according to Fig. 6, both the connection (green) and the damage (red) are marked. This immediately provides a visual representation of the severity of the damage.



Fig. 6: Lateral connection incompletely integrated


The advantage of “machine learning image segmentation” is that the geometries of the damage and contamination can be evaluated via the pixel information. These evaluations can then be provided as information to the engineer directly or to downstream applications. This makes it much easier to identify the severity of the damage.


Another advantage of machine learning image segmentation is that fewer manual annotations are needed to train the models. In our project, we nevertheless performed far more than 1000 such manual annotations.


On the other hand, the core competence of LeanBI is to generate high-quality machine learning models even with little training data. In addition to the selection of the models, the so-called “augmentation”, i.e., the artificial expansion of the image material for training purposes, plays a decisive role.


However, we do not want to conceal one disadvantage of “machine learning image segmentation”. The manual annotation must be carried out very precisely, otherwise the artificial intelligence will not work well enough. Therefore, we have implemented all annotations internally in the project by specialists and deliberately did not use external forces.


The aim of the project was to achieve a “recall” of almost 100%. This means that we do not miss any damage or contamination within the defined damage classes. This is because not detecting damage is far more problematic than falsely reporting damage from time to time. In this case, the engineer can detect such a “false positive” in the inspection process by simply pressing a button. We have achieved this goal for several damage classes, and the artificial intelligence will learn a few others over time, since the engineers provide continuous feedback to the application.


And this brings us back to the topic of how artificial intelligence supports the engineer. The engineer should concentrate on the difficult and rare cases such as root inclusions or infiltrations, while for the frequent cases such as cracks, deposits, deformations, etc., the engineer is supported by artificial intelligence in monitoring and documentation. This not only makes the engineer more efficient, but also improves the quality of his work. The engineer still has at least the important control function.


The present recognition software is set up in such a way that it can be integrated into an existing inspection tool such as KINS. The image data is exported from the inspection software, runs through the automated recognition and annotation process, and is then imported back into the inspection software. There, the image data can then be checked, post-processed and documented by the engineer.


If damage is detected better and earlier, renewals will take place instead of replacements and fewer redevelopment s that would not have been necessary at all. This leads to a reduction in redevelopment costs. And something is also done for people and the environment: qualitatively better monitoring prevents unintentional sewerage pipeline leaks into the environment and infiltrations in freshwater pipes.


We are convinced that with the help of artificial intelligence in combination with PANO technology, around half to two-thirds of today’s recognition errors can be eliminated. Accompanying this estimate is that visual limitations such as poor lighting, poor image resolution, or poor visibility due to debris will also be reduced. In the coming years, imaging technology should improve with the increased use of PANO technology.


[1] Redevelopment case sewerage system, Max Maurer, Sabine Hoffmann | 21.05.2019

[2] Environmental enforcement, communication on water protection No. 42, costs of sewerage disposal, 2003.

[3] Guideline for calculating the value maintenance costs of sewerage plants, page 70, environment, and energy (uwe), canton of Lucerne, 2019.

Postcard from the 16th Unternehmertagung at ASTRA

Picture: Marc Tesch during the presentation


LeanBI presented automated damage detection on engineering structures with Deep Learning at the 16th Unternehmertagung at ASTRA.



  1. AI technology brings massive efficiency gains to engineering structure inspections.
  2. AI technology for damage detection is available and practical. With good image quality, AI detection is already good and will be much better in the future.
  3. The quality of the image data is key and needs to be controlled.
  4. Even if the technology is there, the transition to AI will take different lengths of time (change management). Service platforms with AI will help to accelerate the change.


Digital retrofit integrates plants into Industry 4.0

LeanBI in trade presses on the topic:


Industry 4.0 has come to stay. Legacy systems can still be put to good use in times of digitalization with the help of sensor and control technology. We have identified six use cases where a digital retrofit is worthwhile.




zdnet.de: Digital retrofit for legacy systems


elektronikpraxis.de: A digital retrofit makes sense in these six areas


INDUSTR.com: Digital retrofit integrates legacy systems into modern workflows


news.it-matchmaker.com: Digital retrofit integrates plants into Industry 4.0


i40-magazin.de: Making legacy systems Industrie 4.0-ready


industry-of-things.de: A digital retrofit makes sense in these areas

Der Maschinenbau: Making legacy systems Industrie 4.0-ready


organisator.ch: Digital retrofit integrates legacy systems into modern workflows


it-production.com: Making legacy systems Industrie 4.0-ready


www.bigdata-insider.de: A digital retrofit makes sense in these areas


service-and-maintenance.com: Making legacy systems Industrie 4.0-ready


iavcworld.de: Digital retrofit integrates legacy systems into modern workflows


m-q.ch: Digital retrofit integrates legacy systems into modern workflows


itiko.de: Digital retrofit integrates legacy systems into modern workflows and Industry 4.0


trovarit.com: Digital retrofit integrates older plants into Industry 4.0

Retrofit 4.0 of existing production systems

Modernization of existing production plants with new sensor technology and artificial intelligence


Digital Twins as digital images of production plants and Smart Factory approaches have been the talk of the town for many years. Nevertheless, such implementations are still the exception rather than the rule. This is not because machine manufacturers are not doing their homework. New generations of machines have various sensors and IIoT interfaces to offer new digital services. But this only partially meets the needs of the manufacturing industry.



In a production plant and subsequent intralogistics, machines have a service life of 20, 30 years and more. The first thing to be replaced is usually the control system, but this replacement is still a long way from the smart factory approach. Existing machines should continue to be operated as long as it makes technical and economic sense.


The central role of sensor technology


In order for existing plants to develop in the direction of the Smart Factory, the following goals must be implemented (Retrofit 4.0):

  • Using data and underlying sensor technology to detect failures at an early stage in order to minimize downtime, known as Predictive Maintenance.
  • Using data and underlying sensor technology to continuously improve the logistics and production process in order to increase the efficiency of the processes in a forward-looking manner – we call this Predictive Performance.
  • To keep the quality of the products consistently high despite the variety and increase in variants in the production process with data and underlying sensor technology – we call this Predictive Quality.

For all these goals of Retrofit 4.0 at the existing production plants, the sensors, the data generated thereby and the data analytics based on them play the central role. Fortunately, the costs for sensors, IIoT, data storage and analytics have been reduced by factors over the last 5 to 10 years. So it is currently worthwhile to retrofit existing plants with new sensor technology. Not all at once, but in order of importance and in phases, just as LeanBI has developed the process methodology in many successful projects.


In addition to conventional vibration, temperature and current measurement technology, LeanBI uses new optical and acoustic sensors in the Smart Factory area. Both sensor types are excellent technologies for predictive maintenance, predictive performance and predictive quality. IIoT and digital twin are not the goal, but only a means to an end.


LeanPredict increases performance of intralogistics systems


This modern sensor technology was used, for example, to detect signs of wear on tilt tray sorters in an intralogistics system. For this purpose, the various systems were equipped with optical and acoustic sensor measuring points at one point. The acoustics of the tilt tray change with increasing wear, and mechanical deformations are also immediately detected by the optical sensor. The sensor data is processed on an industrial PC near the plant and continuously transmitted to LeanBI AG’s LeanPredict platform. The data stored in the cloud is analyzed by Artificial Intelligence, for which LeanBI has trained separate machine learning models for many defects. About 20 features are the input parameters for the respective models.


This results in a quality measure with an associated defect value for each wagon and passage at the measuring point. If there is a massive deviation, the wagon must be inspected within 24 hours. A message is sent to the person responsible for the system, a dashboard shows additional information, or a service order is automatically triggered in the maintenance tool.


Picture: Tilt tray sorter of an intralogistics system


Continuous improvement thanks to Artificial Intelligence


Such machine learning models, collectively referred to as Artificial Intelligence, solve different Smart Factory use cases for Retrofit 4.0:

  • They can detect quality problems on the machine or product within fractions of a second by image recognition. Depending on the use case, complex 3D systems or very inexpensive cameras are used.
  • Image recognition evaluates the quality of execution in the case of manual interventions by production personnel.
  • Image recognition supports the traceability and tracking of educts and products in the production process.
  • Acoustics evaluates anomalies at the components or can globally uncover inefficiencies in production.

So this is much more than just being able to determine damage and wear on the machines in a contactless and cost-effective way, as we demonstrate in our specific case of the intralogistics system:


If the quality measure has not yet reached the threshold value, there is a slight defect and the wagon is monitored further. If the damage increases over the days or if there is a larger amount of such minor defects, then a scheduled inspection and maintenance takes place on these wagons. Scheduling maintenance in smaller units throughout the year takes pressure off the maintenance staff, improves diagnostics, reduces work in the major maintenance cycles, and improves the quality rate of sorted parcels. Each detected anomaly is added to the data collection and contributes to the training of the neural network. As a result, the performance of the plant is even constantly improving.


LeanPredict as a technical solution


LeanBI has further developed the LeanPredict framework over various successful smart factory projects. It includes a set of sensors, on-site data processing in an IIoT environment and data analytics based on various machine learning models in the LeanBI Cloud.


Image: LeanPredict framework with connectors


The solution can be set up in a network completely separate from the production. Or the framework can be integrated into the closed production environment so that no data need leave the production network. Either way, the solution is coherent with our customers’ IT security, a must-have criterion for all manufacturers.


More flexibility for plant operators


The pressure to increase efficiency for plant operators will continue to increase. In addition to the well-known goals such as time and cost savings and quality improvement, further flexibilization of production is becoming more important. The successful implementation of this transformation requires from companies to make significant investments in adapting or expanding their production infrastructure. The introduction or expansion of innovative, digital, efficient and ecologically sustainable solutions such as LeanPredict thus contributes to accelerating the upcoming transformation process cost-effectively.

Data science specialist Leanbi strengthens growth course

LeanBI in trade presses on the topic:


We are further expanding our sales activities in the DACH region. The focus here is on digital retrofit and damage detection with the help of machine learning algorithms.


itbusiness.ch: Data science specialist Leanbi strengthens growth course

itiko.de: Data science specialist Leanbi strengthens growth course

IAVCworld.de: Data science specialist Leanbi strengthens growth course